Research topic
I want to find recent papers on using generative AI for creating agent-like pipelines, especially in the context of coding assistants that can manage an entire codebase, including the architectural design, training methodologies, real-world applications, and performance metrics.
Report
Detailed summary
Several papers discuss generative AI for creating agent-like pipelines that manage entire codebases, including key aspects like architecture design, training methodologies, real-world applications, and performance metrics.
For instance, AutoCoder [1] excels in code evaluation through an agent interaction and execution-verified tuning approach, showing notable performance on the HumanEval benchmark. CodeAgent [3] details an LLM-based framework specifically for repository-level code generation with improved performance on real-world tasks. AutoDev [5] presents a comprehensive AI framework for automated software development, covering autonomous codebase management tasks. These papers collectively highlight the progression in employing generative AI to advance coding assistants capable of managing complete software development processes.
Categories of papers
The most important categories to highlight are those that directly address using generative AI for agent-like pipelines and coding assistants managing entire codebases, followed by categories focusing on architecture design, training methodologies, real-world applications, and performance metrics. This structured approach aids in easily identifying relevant research that meets the specified criteria of complex, real-world coding assistant systems.
Generative AI for Agent-Like Pipelines/Coding Assistants Managing Entire Codebases Description: Studies focused on utilizing generative AI to create agent systems capable of managing entire software development processes, including various coding tasks across a codebase. References: [1, 3, 5, 6, 7, 9, 11, 16, 21, 36]
Architectural Design of Generative AI Systems Description: Papers detailing the architectural frameworks and system designs for implementing generative AI in coding assistants and agent-like pipelines. References: [5, 6, 11, 14, 26, 30, 56]
Training Methodologies for Generative AI in Software Development Description: Research focused on the training methods for AI models used in code generation, including self-supervised learning, few-shot learning, and execution-verified tuning. References: [1, 6, 8, 13, 19, 34, 44, 75]
Performance Metrics and Real-World Applications Description: Studies providing evaluation metrics and real-world application examples for AI-driven coding assistants, including benchmarks like HumanEval and practical deployment reports. References: [1, 3, 7, 19, 21, 24, 33, 36]
These categories encapsulate the core areas of interest and present a concise guide to the most pertinent research.
Timeline and citation network
Discovery progress: ~82.4% complete (~32-84 papers found)
So far, I've closely analyzed 540 of the most promising papers, and I've found
~32-84
papers with relevant abstracts, which is probably
~82.4%
of all that exist.
To get this estimate, we do a statistical analysis of the discovery process.
References
Show only:
Last 5 years
Last 2 years
> 1 citation per year
> 5 citations per year
Topic Match
Cit./Year
Year
Paper
Paper Relevance Summary
98.1%
0.0
2024
[1] AutoCoder: Enhancing Code Large Language Model with \textsc{AIEV-Instruct}
Journal Not Provided
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
98.1%
topic match
What the paper does:
Introduces AutoCoder, surpassing GPT-4 models in code evaluation.
Expanded detail:
What the paper does:
Introduces AutoCoder, surpassing GPT-4 models in code evaluation.
Expanded detail:
97.9%
24.8
2023
[2] CodePlan: Repository-level Coding using LLMs and Planning
ArXiv
2023 - 27 citations
-
Show abstract
-
Cite
- PDF
97.9%
topic match
Provides a framework for repository-level coding using LLMs and planning.
CodePlan creates multi-step plans integrating LLM calls for complex codebase changes.
Focuses on dependency and change analysis, enhancing LLM's utility in large codebases.
Provides a framework for repository-level coding using LLMs and planning.
CodePlan creates multi-step plans integrating LLM calls for complex codebase changes.
Focuses on dependency and change analysis, enhancing LLM's utility in large codebases.
97.2%
9.1
2024
[3] CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges
ArXiv
2024 - 7 citations
-
Show abstract
-
Cite
- PDF
97.2%
topic match
Presents CodeAgent, an LLM-based framework for repo-level code generation.
Introduces CodeAgentBench for benchmarking LLMs on complex repository tasks, showing improved performance using integrated programming tools.
Evaluates performance with concrete metrics and real-world scenarios like HumanEval, relevant to the desired topic.
Presents CodeAgent, an LLM-based framework for repo-level code generation.
Introduces CodeAgentBench for benchmarking LLMs on complex repository tasks, showing improved performance using integrated programming tools.
Evaluates performance with concrete metrics and real-world scenarios like HumanEval, relevant to the desired topic.
97.1%
0.0
2024
[4] MapCoder: Multi-Agent Code Generation for Competitive Problem Solving
Journal Not Provided
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
97.1%
topic match
Introduces a multi-agent framework for code generation.
Uses four LLM agents to emulate human-like program synthesis, achieving state-of-the-art results on multiple benchmarks.
Focuses on competitive problem-solving, with performance metrics including HumanEval and MBPP, demonstrating real-world application relevance.
Introduces a multi-agent framework for code generation.
Uses four LLM agents to emulate human-like program synthesis, achieving state-of-the-art results on multiple benchmarks.
Focuses on competitive problem-solving, with performance metrics including HumanEval and MBPP, demonstrating real-world application relevance.
97.0%
0.0
2024
[5] AutoDev: Automated AI-Driven Development
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
97.0%
topic match
Proposes an AI-driven framework for automated software development.
Details autonomous AI agents managing entire codebases, including builds, testing, and git operations.
Mentions use of contextual information, secure environments, and execution of tasks autonomously, covering several specified criteria.
Proposes an AI-driven framework for automated software development.
Details autonomous AI agents managing entire codebases, including builds, testing, and git operations.
Mentions use of contextual information, secure environments, and execution of tasks autonomously, covering several specified criteria.
96.9%
9.7
2024
[6] CodePori: Large Scale Model for Autonomous Software Development by Using Multi-Agents
ArXiv
2024 - 7 citations
-
Show abstract
-
Cite
- PDF
96.9%
topic match
Introduces CodePori for autonomous software development using LLM-based multi-agents.
CodePori performs tasks like system design, code development, review, verification, and testing autonomously.
Evaluates performance using benchmarks like HumanEval and MBPP, demonstrating improved code generation for large projects.
Introduces CodePori for autonomous software development using LLM-based multi-agents.
CodePori performs tasks like system design, code development, review, verification, and testing autonomously.
Evaluates performance using benchmarks like HumanEval and MBPP, demonstrating improved code generation for large projects.
95.9%
0.0
2023
[7] AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation
Journal Not Provided
2023 - 0 citations
-
Show abstract
-
Cite
- PDF
95.9%
topic match
Introduces AgentCoder, a multi-agent framework for code generation.
Utilizes specialized agents for code generation, test case design, and execution.
Demonstrates enhanced performance via iterative testing and optimization, surpassing traditional models and single-agent systems.
Introduces AgentCoder, a multi-agent framework for code generation.
Utilizes specialized agents for code generation, test case design, and execution.
Demonstrates enhanced performance via iterative testing and optimization, surpassing traditional models and single-agent systems.
95.7%
0.0
2024
[8] AICoderEval: Improving AI Domain Code Generation of Large Language Models
Journal Not Provided
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
95.7%
topic match
Provides an evaluation framework for AI-driven code generation.
Enhances and tests LLMs on real-world tasks using the AICoderEval dataset.
Introduces CoderGen, an agent-based framework, aligning with the topic's focus on generative AI for agent-like pipelines.
Provides an evaluation framework for AI-driven code generation.
Enhances and tests LLMs on real-world tasks using the AICoderEval dataset.
Introduces CoderGen, an agent-based framework, aligning with the topic's focus on generative AI for agent-like pipelines.
95.1%
3.5
2024
[9] MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution
ArXiv
2024 - 2 citations
-
Show abstract
-
Cite
- PDF
95.1%
topic match
Proposes an LLM-based multi-agent framework for GitHub issue resolution.
Features different agents like Manager, Repository Custodian, Developer, and QA Engineer collaborating to manage software evolution.
Uses empirical studies and experimental comparisons with GPT-3.5, GPT-4, and Claude-2, showing significant improvements in issue resolution.
Proposes an LLM-based multi-agent framework for GitHub issue resolution.
Features different agents like Manager, Repository Custodian, Developer, and QA Engineer collaborating to manage software evolution.
Uses empirical studies and experimental comparisons with GPT-3.5, GPT-4, and Claude-2, showing significant improvements in issue resolution.
95.0%
12.7
2023
[10] AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation
ArXiv
2023 - 23 citations
-
Show abstract
-
Cite
95.0%
topic match
Introduces a multi-agent framework for iterative code generation and optimization.
Features specialized agents for programming, test design, and test execution to collaboratively refine codes based on feedback.
Evaluates performance using benchmarks like HumanEval, relevant for assessing real-world applicability and performance metrics.
Introduces a multi-agent framework for iterative code generation and optimization.
Features specialized agents for programming, test design, and test execution to collaboratively refine codes based on feedback.
Evaluates performance using benchmarks like HumanEval, relevant for assessing real-world applicability and performance metrics.
94.7%
3.5
2024
[11] CodeS: Natural Language to Code Repository via Multi-Layer Sketch
ArXiv
2024 - 2 citations
-
Show abstract
-
Cite
- PDF
94.7%
topic match
Shows generative AI's potential for creating entire code repositories.
Introduces NL2Repo to generate fully functional code repositories from natural language requirements using the CodeS framework.
Proposes a multi-layer sketch approach, closely aligning with the architectural design and task decomposition aspects specified.
Shows generative AI's potential for creating entire code repositories.
Introduces NL2Repo to generate fully functional code repositories from natural language requirements using the CodeS framework.
Proposes a multi-layer sketch approach, closely aligning with the architectural design and task decomposition aspects specified.
94.2%
3.4
2024
[12] When LLM-based Code Generation Meets the Software Development Process
ArXiv
2024 - 2 citations
-
Show abstract
-
Cite
- PDF
94.2%
topic match
Introduces an LLM-based code generation framework, LCG.
LCG uses multiple LLM agents emulating software process roles with models like LCGScrum, showing notable benchmark improvements.
Evaluates performance on code generation using benchmarks such as HumanEval, showcasing an average 15% improvement over GPT.
Introduces an LLM-based code generation framework, LCG.
LCG uses multiple LLM agents emulating software process roles with models like LCGScrum, showing notable benchmark improvements.
Evaluates performance on code generation using benchmarks such as HumanEval, showcasing an average 15% improvement over GPT.
94.1%
72.3
2023
[13] Self-collaboration Code Generation via ChatGPT
ArXiv
2023 - 110 citations
-
Show abstract
-
Cite
- PDF
94.1%
topic match
Proposes a self-collaboration framework using LLMs for code generation.
Multiple LLM agents act as specialized experts to collaboratively generate code without human intervention.
Employs analysis, coding, and testing stages, demonstrating significant performance improvements in code generation benchmarks.
Proposes a self-collaboration framework using LLMs for code generation.
Multiple LLM agents act as specialized experts to collaboratively generate code without human intervention.
Employs analysis, coding, and testing stages, demonstrating significant performance improvements in code generation benchmarks.
93.4%
0.0
2023
[14] Human like programming using SPADE BDI agents and the GPT-3-based Transformer
Human Interaction and Emerging Technologies (IHIET-AI 2023): Artificial
Intelligence and Future Applications
2023 - 0 citations
-
Show abstract
-
Cite
93.4%
topic match
Provides an architecture for creating virtual developers using SPADE BDI agents and GPT-3.
Combines keyword extraction, requirements synthesis, and source code generation orchestrated by intelligent agents.
Focuses on leveraging GPT-3 for code generation with an agent framework, relevant to managing codebases and architectural design.
Provides an architecture for creating virtual developers using SPADE BDI agents and GPT-3.
Combines keyword extraction, requirements synthesis, and source code generation orchestrated by intelligent agents.
Focuses on leveraging GPT-3 for code generation with an agent framework, relevant to managing codebases and architectural design.
92.2%
0.0
2023
[15] AI Pair Programming Tool
International Journal for Research in Applied Science and Engineering Technology
2023 - 0 citations
-
Show abstract
-
Cite
92.2%
topic match
Provides integration of generative AI with IntelliJ IDEA for coding assistance.
Enhances code suggestions, auto-completions, and error detection using OpenAI’s deep learning models.
Discusses architecture, training methodologies, and empirical performance, focusing on context-aware recommendations in real-world scenarios.
Provides integration of generative AI with IntelliJ IDEA for coding assistance.
Enhances code suggestions, auto-completions, and error detection using OpenAI’s deep learning models.
Discusses architecture, training methodologies, and empirical performance, focusing on context-aware recommendations in real-world scenarios.
92.1%
24.0
2024
[16] OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement
ArXiv
2024 - 16 citations
-
Show abstract
-
Cite
- PDF
92.1%
topic match
Introduces OpenCodeInterpreter for code generation, execution, and refinement.
Integrates execution capabilities and dynamic code refinement with human feedback; evaluated using benchmarks like HumanEval and MBPP.
Highlights significant performance metrics and insight into practical applications in real-world coding tasks.
Introduces OpenCodeInterpreter for code generation, execution, and refinement.
Integrates execution capabilities and dynamic code refinement with human feedback; evaluated using benchmarks like HumanEval and MBPP.
Highlights significant performance metrics and insight into practical applications in real-world coding tasks.
90.1%
47.0
2023
[17] Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents
ArXiv
2023 - 65 citations
-
Show abstract
-
Cite
- PDF
90.1%
topic match
Shows a novel multi-agent framework for enhancing LLM capabilities.
Demonstrates application through case studies, including software development scenarios.
Examines systems like Auto-GPT, addresses collaboration, scalability, and ethical considerations.
Shows a novel multi-agent framework for enhancing LLM capabilities.
Demonstrates application through case studies, including software development scenarios.
Examines systems like Auto-GPT, addresses collaboration, scalability, and ethical considerations.
88.1%
1.6
2024
[18] DevBench: A Comprehensive Benchmark for Software Development
ArXiv
2024 - 1 citations
-
Show abstract
-
Cite
- PDF
88.1%
topic match
Provides a comprehensive benchmark for evaluating LLMs in software development lifecycle tasks.
Covers stages like design, setup, implementation, and testing, assessing models like GPT-4-Turbo.
Highlights current LLMs' shortcomings in understanding complex code structures and managing compilation, offering insights for future developments.
Provides a comprehensive benchmark for evaluating LLMs in software development lifecycle tasks.
Covers stages like design, setup, implementation, and testing, assessing models like GPT-4-Turbo.
Highlights current LLMs' shortcomings in understanding complex code structures and managing compilation, offering insights for future developments.
87.6%
5.3
2024
[19] EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositories
ArXiv
2024 - 3 citations
-
Show abstract
-
Cite
- PDF
87.6%
topic match
Provides a new code generation benchmark (EvoCodeBench).
Aligns with real-world code repositories; includes robust evaluation metrics like Pass@k and Recall@k.
Evaluates 10 popular LLMs for repository-level code generation using an automatically updating pipeline.
Provides a new code generation benchmark (EvoCodeBench).
Aligns with real-world code repositories; includes robust evaluation metrics like Pass@k and Recall@k.
Evaluates 10 popular LLMs for repository-level code generation using an automatically updating pipeline.
86.6%
None
None
[20] Early Results
Journal Not Provided
None - 25 citations
-
Show abstract
-
Cite
86.6%
topic match
Shows use of ChatGPT in a real-world software engineering project.
Demonstrates ChatGPT's potential to implement complete systems and divide coding tasks efficiently in a financial software platform.
Highlights improvements in ChatGPT-4, focusing on coherence and task management, relevant to real-world coding assistant applications.
Shows use of ChatGPT in a real-world software engineering project.
Demonstrates ChatGPT's potential to implement complete systems and divide coding tasks efficiently in a financial software platform.
Highlights improvements in ChatGPT-4, focusing on coherence and task management, relevant to real-world coding assistant applications.
86.3%
10.8
2023
[21] SelfEvolve: A Code Evolution Framework via Large Language Models
ArXiv
2023 - 15 citations
-
Show abstract
-
Cite
- PDF
86.3%
topic match
Develops a two-step pipeline using large language models (LLMs).
Leverages LLMs as knowledge providers and self-reflective programmers.
Discusses enhancing code generation using both retrieval-based methods and self-improvement strategies.
Develops a two-step pipeline using large language models (LLMs).
Leverages LLMs as knowledge providers and self-reflective programmers.
Discusses enhancing code generation using both retrieval-based methods and self-improvement strategies.
84.7%
0.0
2024
[22] Experimenting a New Programming Practice with LLMs
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
84.7%
topic match
Develops AISD, an AI-aided software development prototype.
Automatic generation of use cases, system designs, and implementations from vague user requirements.
Emphasizes user feedback and testing; lacks detailed architectural design and performance metrics discussions.
Develops AISD, an AI-aided software development prototype.
Automatic generation of use cases, system designs, and implementations from vague user requirements.
Emphasizes user feedback and testing; lacks detailed architectural design and performance metrics discussions.
84.7%
1.8
2023
[23] Software Engineering Using Autonomous Agents: Are We There Yet?
2023 38th IEEE/ACM International Conference on Automated Software Engineering (ASE)
2023 - 2 citations
-
Show abstract
-
Cite
84.7%
topic match
Explores autonomous agents in software engineering with LLMs.
Discusses capabilities, challenges, and opportunities using context-rich prompts for accurate task comprehension.
Utilizes Auto-GPT based on GPT-3.5 and GPT-4 for task execution, relevant to agent-like pipelines.
Explores autonomous agents in software engineering with LLMs.
Discusses capabilities, challenges, and opportunities using context-rich prompts for accurate task comprehension.
Utilizes Auto-GPT based on GPT-3.5 and GPT-4 for task execution, relevant to agent-like pipelines.
83.7%
2.6
2024
[24] Teaching Code LLMs to Use Autocompletion Tools in Repository-Level Code Generation
ArXiv
2024 - 2 citations
-
Show abstract
-
Cite
- PDF
83.7%
topic match
Introduces ToolGen for repository-level code generation using code LLMs.
Leverages autocompletion tools to resolve dependencies in repository-level code.
Evaluates effectiveness through a benchmark of 680 real-world code repositories, focusing on dependency errors.
Introduces ToolGen for repository-level code generation using code LLMs.
Leverages autocompletion tools to resolve dependencies in repository-level code.
Evaluates effectiveness through a benchmark of 680 real-world code repositories, focusing on dependency errors.
82.8%
56.0
2023
[25] SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
ArXiv
2023 - 58 citations
-
Show abstract
-
Cite
- PDF
82.8%
topic match
Shows: Evaluates language models on their ability to resolve real-world GitHub issues.
Details: Models need to edit codebases by coordinating changes across multiple elements and files.
Relevance: Discusses limitations in current generative models, indicating challenges in managing entire codebases. Limited by performance on complex tasks.
Shows: Evaluates language models on their ability to resolve real-world GitHub issues.
Details: Models need to edit codebases by coordinating changes across multiple elements and files.
Relevance: Discusses limitations in current generative models, indicating challenges in managing entire codebases. Limited by performance on complex tasks.
82.5%
3.4
2023
[26] Autonomous Agents in Software Development: A Vision Paper
ArXiv
2023 - 3 citations
-
Show abstract
-
Cite
- PDF
82.5%
topic match
Explores the potential of GPT agents in Software Engineering.
Proposes leveraging multiple GPT agents for tasks like project planning, requirements engineering, and software design.
Initial experiments with simple software show high-quality code generation and documentation, indicating promising efficiency and scalability.
Explores the potential of GPT agents in Software Engineering.
Proposes leveraging multiple GPT agents for tasks like project planning, requirements engineering, and software design.
Initial experiments with simple software show high-quality code generation and documentation, indicating promising efficiency and scalability.
81.4%
21.6
2023
[27] Refining ChatGPT-Generated Code: Characterizing and Mitigating Code Quality Issues
ArXiv
2023 - 27 citations
-
Show abstract
-
Cite
- PDF
81.4%
topic match
Provides a systematic study on the quality of ChatGPT-generated code.
Analyzes correctness, factors influencing effectiveness, and potential issues in ChatGPT’s code generation.
Focuses on code quality issues, not on managing entire codebases or agent-like pipelines.
Provides a systematic study on the quality of ChatGPT-generated code.
Analyzes correctness, factors influencing effectiveness, and potential issues in ChatGPT’s code generation.
Focuses on code quality issues, not on managing entire codebases or agent-like pipelines.
78.0%
0.0
2023
[28] Towards Trustworthy AI Software Development Assistance
https://doi.org/10.1145/3639476.3639770
2023 - 0 citations
-
Show abstract
-
Cite
- PDF
78.0%
topic match
Provides a holistic architecture for trustworthy AI software development assistants
Focuses on constructing, training, and using LLMs fine-tuned on code quality and correctness criteria
Integrates graph-based code representations and a knowledge graph, but does not detail complete agent-like pipeline management
Provides a holistic architecture for trustworthy AI software development assistants
Focuses on constructing, training, and using LLMs fine-tuned on code quality and correctness criteria
Integrates graph-based code representations and a knowledge graph, but does not detail complete agent-like pipeline management
78.0%
1.0
2023
[29] End-to-End Software Construction using ChatGPT: An Experience Report
ArXiv
2023 - 1 citations
-
Show abstract
-
Cite
- PDF
78.0%
topic match
The paper explores using ChatGPT for end-to-end software construction.
It documents prompt categories (initialization, feature requests, bug-fixing, layout) and compares outputs with manually implemented apps.
Discusses top-down and bottom-up prompt techniques, indicating practical application insights and limitations.
The paper explores using ChatGPT for end-to-end software construction.
It documents prompt categories (initialization, feature requests, bug-fixing, layout) and compares outputs with manually implemented apps.
Discusses top-down and bottom-up prompt techniques, indicating practical application insights and limitations.
77.5%
3.1
2024
[30] Language Agents as Optimizable Graphs
ArXiv
2024 - 2 citations
-
Show abstract
-
Cite
- PDF
77.5%
topic match
Describes: Using LLM agents as optimizable computational graphs.
Details: Focuses on refining LLM prompts and agent orchestration within graph structures.
Relevance: Emphasizes developing and optimizing LLM-based agents, implying potential applications in managing codebases through agent-like pipelines.
Describes: Using LLM agents as optimizable computational graphs.
Details: Focuses on refining LLM prompts and agent orchestration within graph structures.
Relevance: Emphasizes developing and optimizing LLM-based agents, implying potential applications in managing codebases through agent-like pipelines.
77.1%
9.7
2023
[31] RepoFusion: Training Code Models to Understand Your Repository
ArXiv
2023 - 13 citations
-
Show abstract
-
Cite
- PDF
77.1%
topic match
Proposes RepoFusion framework for enhanced code completions.
Trains models to incorporate repository context for accurate completions.
Focuses on context within the repository, not the entire codebase nor agent-like pipelines.
Proposes RepoFusion framework for enhanced code completions.
Trains models to incorporate repository context for accurate completions.
Focuses on context within the repository, not the entire codebase nor agent-like pipelines.
77.0%
53.1
2022
[32] A Conversational Paradigm for Program Synthesis
ArXiv
2022 - 149 citations
-
Show abstract
-
Cite
77.0%
topic match
Proposes a conversational program synthesis approach via large language models.
Focuses on generating code through a multi-turn conversation to capture user intent.
Trains models on natural and programming languages, introduces new benchmark for multi-step synthesis, relevant for coding assistants.
Proposes a conversational program synthesis approach via large language models.
Focuses on generating code through a multi-turn conversation to capture user intent.
Trains models on natural and programming languages, introduces new benchmark for multi-step synthesis, relevant for coding assistants.
74.3%
0.0
2024
[33] DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories
Journal Not Provided
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
74.3%
topic match
Proposes a benchmark named DevEval for evaluating LLMs on real-world code.
Aligns with real-world code repositories and includes comprehensive annotations and samples from multiple domains.
Evaluates coding abilities of popular LLMs, revealing performance metrics relevant to generative AI coding assistants.
Proposes a benchmark named DevEval for evaluating LLMs on real-world code.
Aligns with real-world code repositories and includes comprehensive annotations and samples from multiple domains.
Evaluates coding abilities of popular LLMs, revealing performance metrics relevant to generative AI coding assistants.
74.0%
40.3
2023
[34] InferFix: End-to-End Program Repair with LLMs
Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering
2023 - 65 citations
-
Show abstract
-
Cite
- PDF
74.0%
topic match
Introduces a program repair framework using transformer-based LLMs.
Combines static analysis with LLMs for fixing security and performance bugs.
Focuses on specific bug-fixing rather than holistic codebase management, lacking architectural design, training methodology, and real-world application analysis.
Introduces a program repair framework using transformer-based LLMs.
Combines static analysis with LLMs for fixing security and performance bugs.
Focuses on specific bug-fixing rather than holistic codebase management, lacking architectural design, training methodology, and real-world application analysis.
73.8%
1.9
2022
[35] A Practical Three-phase Approach To Fully Automated Programming Using System Decomposition And Coding Copilots
Proceedings of the 2022 5th International Conference on Machine Learning and Machine Intelligence
2022 - 4 citations
-
Show abstract
-
Cite
73.8%
topic match
Proposes a neuro-symbolic approach using VLS models for automated programming.
Divides the coding task into hierarchical tasks, function completion, and handling corner cases, fully automating the process with language models.
Includes empirical insights, prompt templates, and practical guidance; relevant for AI-driven coding assistants but lacks detailed architecture and training methodologies specifics.
Proposes a neuro-symbolic approach using VLS models for automated programming.
Divides the coding task into hierarchical tasks, function completion, and handling corner cases, fully automating the process with language models.
Includes empirical insights, prompt templates, and practical guidance; relevant for AI-driven coding assistants but lacks detailed architecture and training methodologies specifics.
73.4%
5.1
2024
[36] DevEval: Evaluating Code Generation in Practical Software Projects
ArXiv
2024 - 4 citations
-
Show abstract
-
Cite
- PDF
73.4%
topic match
Proposes a new benchmark for evaluating code generation.
DevEval aligns with practical software projects and assesses LLMs on realistic tasks.
Reveals LLM performance on real-world tasks but doesn't cover full agent-like pipeline management.
Proposes a new benchmark for evaluating code generation.
DevEval aligns with practical software projects and assesses LLMs on realistic tasks.
Reveals LLM performance on real-world tasks but doesn't cover full agent-like pipeline management.
72.4%
0.0
2024
[37] Towards Autonomous Tool Utilization in Language Models: A Unified, Efficient and Scalable Framework
International Conference on Language Resources and Evaluation
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
72.4%
topic match
Provides a unified framework for autonomous tool utilization in language models.
Unifies sequential decision-making for tool engagement, fine-tuned on diverse APIs with efficient data annotation.
Includes dynamic rehearsal for continual learning, enhancing scalability and surpassing GPT-3.5/4 in multiple metrics.
Provides a unified framework for autonomous tool utilization in language models.
Unifies sequential decision-making for tool engagement, fine-tuned on diverse APIs with efficient data annotation.
Includes dynamic rehearsal for continual learning, enhancing scalability and surpassing GPT-3.5/4 in multiple metrics.
71.6%
188.3
2023
[38] MetaGPT: Meta Programming for Multi-Agent Collaborative Framework
ArXiv
2023 - 231 citations
-
Show abstract
-
Cite
- PDF
71.6%
topic match
Shows potential of MetaGPT in multi-agent collaborative frameworks.
Generates coherent and correct coding solutions, better than chat-based systems.
Public GitHub repository is available for reproducibility and further exploration.
Shows potential of MetaGPT in multi-agent collaborative frameworks.
Generates coherent and correct coding solutions, better than chat-based systems.
Public GitHub repository is available for reproducibility and further exploration.
70.2%
4.9
2023
[39] GitAgent: Facilitating Autonomous Agent with GitHub by Tool Extension
ArXiv
2023 - 4 citations
-
Show abstract
-
Cite
- PDF
70.2%
topic match
Introduces GitAgent for autonomous tool extension using GitHub repositories.
GitAgent integrates repositories into its toolset autonomously, leveraging GitHub Issues/PRs to solve problems, achieving a 69.4% success rate.
Relevant to coding assistants managing codebases; limited focus on training methodologies and performance metrics for entire agent-like pipelines.
Introduces GitAgent for autonomous tool extension using GitHub repositories.
GitAgent integrates repositories into its toolset autonomously, leveraging GitHub Issues/PRs to solve problems, achieving a 69.4% success rate.
Relevant to coding assistants managing codebases; limited focus on training methodologies and performance metrics for entire agent-like pipelines.
68.9%
12.7
2023
[40] xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval
ArXiv
2023 - 23 citations
-
Show abstract
-
Cite
68.9%
topic match
Provides a benchmark for evaluating code understanding, generation, translation, and retrieval.
Focuses on pre-trained language models and their performance on various code-related tasks across multiple languages.
Lacks specifics on generative AI for managing entire codebases and detailed architectural/training methodologies, but useful for performance metrics and real-world applications evaluation.
Provides a benchmark for evaluating code understanding, generation, translation, and retrieval.
Focuses on pre-trained language models and their performance on various code-related tasks across multiple languages.
Lacks specifics on generative AI for managing entire codebases and detailed architectural/training methodologies, but useful for performance metrics and real-world applications evaluation.
68.8%
6.1
2023
[41] From Copilot to Pilot: Towards AI Supported Software Development
ArXiv
2023 - 10 citations
-
Show abstract
-
Cite
- PDF
68.8%
topic match
Describes the evolution of AI-supported software engineering.
Discusses moving from code completion (Copilot) to more holistic software engineering tasks.
Mentions avoiding code smells and following language idioms, but lacks details on training methodologies or performance metrics.
Describes the evolution of AI-supported software engineering.
Discusses moving from code completion (Copilot) to more holistic software engineering tasks.
Mentions avoiding code smells and following language idioms, but lacks details on training methodologies or performance metrics.
67.6%
32.2
2024
[42] If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents
ArXiv
2024 - 26 citations
-
Show abstract
-
Cite
- PDF
67.6%
topic match
Describes how code integration enhances LLMs' capabilities.
Outlines how code helps LLMs in reasoning, structure, and execution.
Highlights the potential of LLMs to function as intelligent agents for complex tasks.
Describes how code integration enhances LLMs' capabilities.
Outlines how code helps LLMs in reasoning, structure, and execution.
Highlights the potential of LLMs to function as intelligent agents for complex tasks.
67.3%
300.2
2021
[43] CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation
ArXiv
2021 - 942 citations
-
Show abstract
-
Cite
- PDF
67.3%
topic match
Introduces CodeT5 for code understanding and generation tasks.
Uses a unified encoder-decoder model with identifier-aware pre-training and multi-task learning.
Focuses more on code semantics rather than full pipeline management, lacking extensive discussion on architectural design and real-world applications.
Introduces CodeT5 for code understanding and generation tasks.
Uses a unified encoder-decoder model with identifier-aware pre-training and multi-task learning.
Focuses more on code semantics rather than full pipeline management, lacking extensive discussion on architectural design and real-world applications.
61.1%
2.1
2024
[44] PECC: Problem Extraction and Coding Challenges
ArXiv
2024 - 1 citations
-
Show abstract
-
Cite
- PDF
61.1%
topic match
Introduces a novel benchmark, PECC, for evaluating LLMs in problem-solving and code generation tasks.
PECC requires LLMs to interpret narrative-embedded problems, extract requirements, and generate executable code, mirroring real-world scenarios.
While it investigates generative AI in coding, it does not specifically address managing entire codebases or agent-like pipelines.
Introduces a novel benchmark, PECC, for evaluating LLMs in problem-solving and code generation tasks.
PECC requires LLMs to interpret narrative-embedded problems, extract requirements, and generate executable code, mirroring real-world scenarios.
While it investigates generative AI in coding, it does not specifically address managing entire codebases or agent-like pipelines.
60.2%
10.1
2023
[45] Generative Artificial Intelligence for Software Engineering - A Research Agenda
ArXiv
2023 - 10 citations
-
Show abstract
-
Cite
- PDF
60.2%
topic match
Provides an overview of GenAI tools in software development.
Details current development, applications, limitations, and challenges of GenAI like ChatGPT and Copilot.
Lacks a detailed focus on agent-like pipelines and specific training methodologies.
Provides an overview of GenAI tools in software development.
Details current development, applications, limitations, and challenges of GenAI like ChatGPT and Copilot.
Lacks a detailed focus on agent-like pipelines and specific training methodologies.
60.0%
2.8
2024
[46] Enhancing LLM-Based Coding Tools through Native Integration of IDE-Derived Static Context
ArXiv
2024 - 2 citations
-
Show abstract
-
Cite
- PDF
60.0%
topic match
Demonstrates methods to enhance LLM-based code completion with IDE-derived contexts.
Proposes IDECoder to leverage accurate, real-time cross-file information for improved repository-level code completion.
Focuses on synergy between IDEs and LLMs but lacks in-depth details on architectural design, training methodologies, or broad real-world applications.
Demonstrates methods to enhance LLM-based code completion with IDE-derived contexts.
Proposes IDECoder to leverage accurate, real-time cross-file information for improved repository-level code completion.
Focuses on synergy between IDEs and LLMs but lacks in-depth details on architectural design, training methodologies, or broad real-world applications.
59.4%
3.9
2023
[47] CoLadder: Supporting Programmers with Hierarchical Code Generation in Multi-Level Abstraction
ArXiv
2023 - 4 citations
-
Show abstract
-
Cite
- PDF
59.4%
topic match
Provides: Hierarchical task decomposition and code manipulation using LLMs for programming.
Details: CoLadder helps programmers format intentions, decompose tasks, and evaluate results, improving goal alignment with generated code.
Potential Relevance: Focuses on prompt authoring and code evaluation rather than agent-like pipeline management or architectural design.
Provides: Hierarchical task decomposition and code manipulation using LLMs for programming.
Details: CoLadder helps programmers format intentions, decompose tasks, and evaluate results, improving goal alignment with generated code.
Potential Relevance: Focuses on prompt authoring and code evaluation rather than agent-like pipeline management or architectural design.
58.9%
16.8
2023
[48] Generative AI for Software Practitioners
IEEE Software
2023 - 22 citations
-
Show abstract
-
Cite
58.9%
topic match
Provides a discussion on generative AI tools in software engineering.
Explores how tools like ChatGPT and CoPilot enhance software productivity, including practical use cases and industry guidance.
Lacks specific focus on agent-like pipelines and detailed metrics for managing entire codebases.
Provides a discussion on generative AI tools in software engineering.
Explores how tools like ChatGPT and CoPilot enhance software productivity, including practical use cases and industry guidance.
Lacks specific focus on agent-like pipelines and detailed metrics for managing entire codebases.
57.2%
0.0
2023
[49] Exploring the intersection of Generative AI and Software Development
ArXiv
2023 - 0 citations
-
Show abstract
-
Cite
- PDF
57.2%
topic match
Relates generative AI to software development processes.
Explores generative AI techniques like zero-shot prompting and multimodal chain-of-thought for enhancing software engineering tasks.
Emphasizes vector embeddings, context tools, and code assistants but lacks specific focus on managing entire codebases and detailed performance metrics.
Relates generative AI to software development processes.
Explores generative AI techniques like zero-shot prompting and multimodal chain-of-thought for enhancing software engineering tasks.
Emphasizes vector embeddings, context tools, and code assistants but lacks specific focus on managing entire codebases and detailed performance metrics.
56.1%
29.3
2022
[50] Repository-Level Prompt Generation for Large Language Models of Code
International Conference on Machine Learning
2022 - 68 citations
-
Show abstract
-
Cite
- PDF
56.1%
topic match
Develops a framework for generating effective prompts for LLMs in code autocompletion.
Incorporates repository structure and context to improve prompt quality and performance.
Develops a framework for generating effective prompts for LLMs in code autocompletion.
Incorporates repository structure and context to improve prompt quality and performance.
55.9%
29.2
2024
[51] Large Language Model based Multi-Agents: A Survey of Progress and Challenges
ArXiv
2024 - 22 citations
-
Show abstract
-
Cite
- PDF
55.9%
topic match
Provides a survey on LLM-based multi-agent systems.
Discusses how LLMs act autonomously for planning, reasoning, and complex problem-solving.
Focuses on multi-agent systems and communication, not specifically on coding assistants managing entire codebases.
Provides a survey on LLM-based multi-agent systems.
Discusses how LLMs act autonomously for planning, reasoning, and complex problem-solving.
Focuses on multi-agent systems and communication, not specifically on coding assistants managing entire codebases.
55.5%
21.4
2023
[52] AI-assisted coding: Experiments with GPT-4
ArXiv
2023 - 32 citations
-
Show abstract
-
Cite
- PDF
55.5%
topic match
Examines: AI code generation using GPT-4.
Details: Highlights the need for human validation to ensure code accuracy.
Relevant Info: Discusses GPT-4's capabilities in code refactoring and test generation, but lacks in-depth focus on agent-like pipelines and performance metrics.
Examines: AI code generation using GPT-4.
Details: Highlights the need for human validation to ensure code accuracy.
Relevant Info: Discusses GPT-4's capabilities in code refactoring and test generation, but lacks in-depth focus on agent-like pipelines and performance metrics.
55.5%
13.9
2024
[53] Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects
ArXiv
2024 - 11 citations
-
Show abstract
-
Cite
- PDF
55.5%
topic match
Provides an overview of LLM-based intelligent agents and their applications.
Explores definitions, frameworks, and foundational components within single and multi-agent systems, including cognitive and planning methods.
Touches on applications in coding but lacks detailed architectural design, training methodologies, and performance metrics for codebase management.
Provides an overview of LLM-based intelligent agents and their applications.
Explores definitions, frameworks, and foundational components within single and multi-agent systems, including cognitive and planning methods.
Touches on applications in coding but lacks detailed architectural design, training methodologies, and performance metrics for codebase management.
55.3%
28.4
2023
[54] Large Language Models for Software Engineering: Survey and Open Problems
2023 IEEE/ACM International Conference on Software Engineering: Future of Software Engineering (ICSE-FoSE)
2023 - 41 citations
-
Show abstract
-
Cite
- PDF
55.3%
topic match
Provides a survey of LLMs for Software Engineering.
Covers applications in coding, design, repair, performance improvement, and documentation.
Discusses challenges like hallucinations and advocates hybrid techniques combining traditional SE with LLMs.
Provides a survey of LLMs for Software Engineering.
Covers applications in coding, design, repair, performance improvement, and documentation.
Discusses challenges like hallucinations and advocates hybrid techniques combining traditional SE with LLMs.
54.5%
25.4
2023
[55] Self-planning Code Generation with Large Language Model
ArXiv
2023 - 41 citations
-
Show abstract
-
Cite
- PDF
54.5%
topic match
Introduces a self-planning approach to code generation using LLMs.
Demonstrates improved code quality and problem-solving by decomposing complex intents into manageable steps.
Focuses on code generation and quality improvement but does not discuss managing entire codebases or agent-like pipelines.
Introduces a self-planning approach to code generation using LLMs.
Demonstrates improved code quality and problem-solving by decomposing complex intents into manageable steps.
Focuses on code generation and quality improvement but does not discuss managing entire codebases or agent-like pipelines.
53.9%
0.0
2024
[56] LLM-Based Multi-Agent Systems for Software Engineering: Vision and the Road Ahead
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
53.9%
topic match
Paper provides: A vision for integrating LLMs into multi-agent systems for software engineering.
Details: Emphasizes cognitive capabilities for autonomous problem-solving and robustness in complex software projects.
Relevance: Focuses on theoretical future applications, not detailed architecture, training methods, or real-world metrics.
Paper provides: A vision for integrating LLMs into multi-agent systems for software engineering.
Details: Emphasizes cognitive capabilities for autonomous problem-solving and robustness in complex software projects.
Relevance: Focuses on theoretical future applications, not detailed architecture, training methods, or real-world metrics.
53.3%
0.0
2023
[57] xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval
Journal Not Provided
2023 - 0 citations
-
Show abstract
-
Cite
- PDF
53.3%
topic match
Provides a benchmark for code-related tasks
Evaluates pre-trained language models on code generation, translation, and retrieval across multiple languages.
Focuses on evaluation metrics rather than managing entire codebases or architectural design.
Provides a benchmark for code-related tasks
Evaluates pre-trained language models on code generation, translation, and retrieval across multiple languages.
Focuses on evaluation metrics rather than managing entire codebases or architectural design.
53.0%
20.3
2023
[58] CoderEval: A Benchmark of Pragmatic Code Generation with Generative Pre-trained Models
International Conference on Software Engineering
2023 - 35 citations
-
Show abstract
-
Cite
- PDF
53.0%
topic match
What the paper does: Proposes a benchmark for pragmatic code generation.
Details: Introduces CoderEval to assess functional correctness of non-standalone generated code in Python and Java.
Relevance: Focuses on evaluating generative AI code models but doesn't cover agent-like pipeline management of entire codebases or detailed training methods.
What the paper does: Proposes a benchmark for pragmatic code generation.
Details: Introduces CoderEval to assess functional correctness of non-standalone generated code in Python and Java.
Relevance: Focuses on evaluating generative AI code models but doesn't cover agent-like pipeline management of entire codebases or detailed training methods.
53.0%
9.8
2023
[59] AI-assisted Code Authoring at Scale: Fine-tuning, deploying, and mixed methods evaluation
Journal Not Provided
2023 - 14 citations
-
Show abstract
-
Cite
- PDF
53.0%
topic match
Shows the deployment of AI-assisted code authoring tools.
Discusses CodeCompose, using InCoder LLM for code suggestion in multiple languages at Meta.
Lacks detailed discussion on architectural design, training methodologies, real-world applications outside Meta, and specific performance metrics.
Shows the deployment of AI-assisted code authoring tools.
Discusses CodeCompose, using InCoder LLM for code suggestion in multiple languages at Meta.
Lacks detailed discussion on architectural design, training methodologies, real-world applications outside Meta, and specific performance metrics.
52.9%
0.0
2024
[60] Fight Fire with Fire: How Much Can We Trust ChatGPT on Source Code-Related Tasks?
Journal Not Provided
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
52.9%
topic match
Assesses ChatGPT's performance on code-related tasks.
Examines ChatGPT's ability to generate and self-verify code and test reports.
Focuses on multi-agent collaborative development, but lacks detailed architectural, real-world applications, and specific training methodologies.
Assesses ChatGPT's performance on code-related tasks.
Examines ChatGPT's ability to generate and self-verify code and test reports.
Focuses on multi-agent collaborative development, but lacks detailed architectural, real-world applications, and specific training methodologies.
52.6%
18.0
2023
[61] Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation
ArXiv
2023 - 19 citations
-
Show abstract
-
Cite
- PDF
52.6%
topic match
Shows the capability of a language model to improve itself.
Uses a language-model-infused scaffolding program for recursive self-improvement of code generation, including GPT-4.
Discusses various self-improvement strategies but lacks details on complete architectural design, training methodologies, and real-world applications in managing entire codebases.
Shows the capability of a language model to improve itself.
Uses a language-model-infused scaffolding program for recursive self-improvement of code generation, including GPT-4.
Discusses various self-improvement strategies but lacks details on complete architectural design, training methodologies, and real-world applications in managing entire codebases.
50.4%
1.4
2024
[62] Generating Java Methods: An Empirical Assessment of Four AI-Based Code Assistants
ArXiv
2024 - 1 citations
-
Show abstract
-
Cite
- PDF
50.4%
topic match
Assesses AI-based code assistants' effectiveness in generating Java methods.
Compares GitHub Copilot, Tabnine, ChatGPT, and Google Bard using a 100-method dataset from real-life Java projects.
Partially relevant: focuses on generative AI for code snippets, but lacks discussion on agent-like pipelines, architectural design, or detailed training methodologies.
Assesses AI-based code assistants' effectiveness in generating Java methods.
Compares GitHub Copilot, Tabnine, ChatGPT, and Google Bard using a 100-method dataset from real-life Java projects.
Partially relevant: focuses on generative AI for code snippets, but lacks discussion on agent-like pipelines, architectural design, or detailed training methodologies.
48.5%
0.0
2024
[63] AI-powered Code Review with LLMs: Early Results
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
48.5%
topic match
Provides: An LLM-based model for code review and quality improvement.
Details: Trained on code repositories to detect issues, suggest improvements, and predict future code risks.
Relevance: Focuses on code quality and developer feedback, less on full codebase management or architectural design.
Provides: An LLM-based model for code review and quality improvement.
Details: Trained on code repositories to detect issues, suggest improvements, and predict future code risks.
Relevance: Focuses on code quality and developer feedback, less on full codebase management or architectural design.
48.2%
2.0
2022
[64] Test-Driven Multi-Task Learning with Functionally Equivalent Code Transformation for Neural Code Generation
Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering
2022 - 4 citations
-
Show abstract
-
Cite
48.2%
topic match
Proposes a novel framework for neural code generation.
Combines program analysis with deep learning, using functionally equivalent code snippets and test execution feedback.
Focuses on functional correctness and introduces test-driven multi-task learning, relevant but doesn’t cover full agent-like pipeline management.
Proposes a novel framework for neural code generation.
Combines program analysis with deep learning, using functionally equivalent code snippets and test execution feedback.
Focuses on functional correctness and introduces test-driven multi-task learning, relevant but doesn’t cover full agent-like pipeline management.
47.0%
18.8
2024
[65] OS-Copilot: Towards Generalist Computer Agents with Self-Improvement
ArXiv
2024 - 13 citations
-
Show abstract
-
Cite
- PDF
47.0%
topic match
Provides a framework for generalist agents called OS-Copilot.
Introduces FRIDAY, a self-improving agent for automating diverse computer tasks including code management.
Focuses on interfacing with a variety of OS elements; includes performance metrics like GAIA benchmark but lacks specifics on generative AI for entire codebase management.
Provides a framework for generalist agents called OS-Copilot.
Introduces FRIDAY, a self-improving agent for automating diverse computer tasks including code management.
Focuses on interfacing with a variety of OS elements; includes performance metrics like GAIA benchmark but lacks specifics on generative AI for entire codebase management.
46.2%
29.5
2024
[66] Understanding the planning of LLM agents: A survey
ArXiv
2024 - 21 citations
-
Show abstract
-
Cite
- PDF
46.2%
topic match
Provides a systematic view of LLM-based agents planning
Offers taxonomy categorizing planning methods including Task Decomposition, Plan Selection, External Module, Reflection, and Memory
Focuses on planning rather than managing entire codebases; may inform architecture and methodologies for generative AI coding assistants
Provides a systematic view of LLM-based agents planning
Offers taxonomy categorizing planning methods including Task Decomposition, Plan Selection, External Module, Reflection, and Memory
Focuses on planning rather than managing entire codebases; may inform architecture and methodologies for generative AI coding assistants
45.7%
0.0
2024
[67] From Language Models to Practical Self-Improving Computer Agents
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
45.7%
topic match
Shows LLMs can self-augment for diverse tasks.
Demonstrates an LLM agent generating its own tools for software development and web tasks using prompt engineering.
Relevant to the extent of detailing self-improving agents but lacks specific focus on entire codebase management and performance metrics.
Shows LLMs can self-augment for diverse tasks.
Demonstrates an LLM agent generating its own tools for software development and web tasks using prompt engineering.
Relevant to the extent of detailing self-improving agents but lacks specific focus on entire codebase management and performance metrics.
45.5%
0.0
2024
[68] Can Github issues be solved with Tree Of Thoughts?
Journal Not Provided
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
45.5%
topic match
Explores ToT framework for solving GitHub issues via LLMs.
Introduces structured exploration and self-assessment for complex problem-solving beyond basic code generation.
Discusses benchmarks like HumanEval but focuses on decision-making, which is slightly tangential to coding assistant pipelines.
Explores ToT framework for solving GitHub issues via LLMs.
Introduces structured exploration and self-assessment for complex problem-solving beyond basic code generation.
Discusses benchmarks like HumanEval but focuses on decision-making, which is slightly tangential to coding assistant pipelines.
44.3%
2.1
2024
[69] Automatic Programming: Large Language Models and Beyond
ArXiv
2024 - 1 citations
-
Show abstract
-
Cite
- PDF
44.3%
topic match
Discusses automated coding using Large Language Models (LLMs).
Considers quality, security, and programmer roles in deploying automated code.
Touches on program repair and analysis but lacks focus on agent-like pipelines and codebase management.
Discusses automated coding using Large Language Models (LLMs).
Considers quality, security, and programmer roles in deploying automated code.
Touches on program repair and analysis but lacks focus on agent-like pipelines and codebase management.
43.7%
0.0
2024
[70] CodeGRAG: Extracting Composed Syntax Graphs for Retrieval Augmented Cross-Lingual Code Generation
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
43.7%
topic match
Improves code generation with Syntax Graph Retrieval.
Uses control and data flow extraction to bridge syntax gaps between programming and natural languages.
Focuses on enhancing single-round and cross-lingual code generation, but lacks discussion on agent-like pipelines and codebase management.
Improves code generation with Syntax Graph Retrieval.
Uses control and data flow extraction to bridge syntax gaps between programming and natural languages.
Focuses on enhancing single-round and cross-lingual code generation, but lacks discussion on agent-like pipelines and codebase management.
43.7%
45.2
2021
[71] Jigsaw: Large Language Models meet Program Synthesis
2022 IEEE/ACM 44th International Conference on Software Engineering (ICSE)
2021 - 130 citations
-
Show abstract
-
Cite
- PDF
43.7%
topic match
Provides: Augments large language models for program synthesis.
Details: Uses program analysis and synthesis techniques to enhance code generation accuracy from natural language.
Additional Info: Focuses on Python Pandas API, utilizing user feedback for continuous improvement; lacks broader codebase management aspects.
Provides: Augments large language models for program synthesis.
Details: Uses program analysis and synthesis techniques to enhance code generation accuracy from natural language.
Additional Info: Focuses on Python Pandas API, utilizing user feedback for continuous improvement; lacks broader codebase management aspects.
43.5%
0.0
2024
[72] On The Importance of Reasoning for Context Retrieval in Repository-Level Code Editing
Journal Not Provided
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
43.5%
topic match
Examines the role of reasoning in context retrieval for repository-level code editing.
Decouples context retrieval from other components, conducting focused experiments on context gathering in codebases.
Details repository navigation using LLMs but lacks comprehensive coverage of architectural design, training methodologies, or performance metrics for generative AI in creating agent-like pipelines.
Examines the role of reasoning in context retrieval for repository-level code editing.
Decouples context retrieval from other components, conducting focused experiments on context gathering in codebases.
Details repository navigation using LLMs but lacks comprehensive coverage of architectural design, training methodologies, or performance metrics for generative AI in creating agent-like pipelines.
43.3%
3.1
2024
[73] When Large Language Models Confront Repository-Level Automatic Program Repair: How Well They Done?
https://doi.org/10.48550/arXiv.2403.00448
2024 - 2 citations
-
Show abstract
-
Cite
- PDF
43.3%
topic match
Provides an evaluation of large language models for repository-level automatic program repair.
Introduces the RepoBugs benchmark and examines repository-level context extraction methods for improving repair success rates.
Focuses on program repair rather than broader agent-like pipelines for managing entire codebases.
Provides an evaluation of large language models for repository-level automatic program repair.
Introduces the RepoBugs benchmark and examines repository-level context extraction methods for improving repair success rates.
Focuses on program repair rather than broader agent-like pipelines for managing entire codebases.
43.2%
0.9
2023
[74] OpenAi's GPT4 as coding assistant
ArXiv
2023 - 1 citations
-
Show abstract
-
Cite
- PDF
43.2%
topic match
Examines GPT3.5 and GPT4 as coding assistants
Tests capabilities in answering questions, code generation, and debugging
Focuses more on productivity improvements than full codebase management
Examines GPT3.5 and GPT4 as coding assistants
Tests capabilities in answering questions, code generation, and debugging
Focuses more on productivity improvements than full codebase management
43.1%
6.7
2024
[75] Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models
ArXiv
2024 - 4 citations
-
Show abstract
-
Cite
- PDF
43.1%
topic match
Provides: Insights on tuning LLMs for agent-based tasks.
Expands: Observes key challenges in current agent training methodologies and identifies issues like data distribution shifts and hallucinations.
Provides: Insights on tuning LLMs for agent-based tasks.
Expands: Observes key challenges in current agent training methodologies and identifies issues like data distribution shifts and hallucinations.
42.5%
18.8
2022
[76] Language Models Can Teach Themselves to Program Better
ArXiv
2022 - 42 citations
-
Show abstract
-
Cite
- PDF
42.5%
topic match
Shows LMs can self-improve via self-generated programming problems.
Demonstrates the use of an interpreter to verify correctness and enhance performance using self-play techniques.
Relevant in testing performance metrics but may lack comprehensive focus on managing entire codebases or agent-like pipelines.
Shows LMs can self-improve via self-generated programming problems.
Demonstrates the use of an interpreter to verify correctness and enhance performance using self-play techniques.
Relevant in testing performance metrics but may lack comprehensive focus on managing entire codebases or agent-like pipelines.
42.5%
6.6
2023
[77] L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language Models
ArXiv
2023 - 7 citations
-
Show abstract
-
Cite
- PDF
42.5%
topic match
Comprehensively evaluates language-to-code generation capabilities of large language models.
Analyzes performance across tasks like semantic parsing, math reasoning, and Python programming using various models and methods.
Includes human evaluations and confidence calibration but lacks focus on managing entire codebases and agent-like pipelines.
Comprehensively evaluates language-to-code generation capabilities of large language models.
Analyzes performance across tasks like semantic parsing, math reasoning, and Python programming using various models and methods.
Includes human evaluations and confidence calibration but lacks focus on managing entire codebases and agent-like pipelines.
41.6%
1.7
2023
[78] Artificial Intelligence-Based Tools in Software Development Processes: Application of ChatGPT
European Journal of Technic
2023 - 2 citations
-
Show abstract
-
Cite
41.6%
topic match
Highlights ChatGPT's role in software development.
Explores code generation, test automation, error analysis, and performance improvements using ChatGPT.
Lacks detailed discussion on managing entire codebases or specific agent-like pipeline architectures.
Highlights ChatGPT's role in software development.
Explores code generation, test automation, error analysis, and performance improvements using ChatGPT.
Lacks detailed discussion on managing entire codebases or specific agent-like pipeline architectures.
39.0%
0.0
2023
[79] Developer Experiences with a Contextualized AI Coding Assistant: Usability, Expectations, and Outcomes
ArXiv
2023 - 0 citations
-
Show abstract
-
Cite
- PDF
39.0%
topic match
Explores usability of contextualized AI coding assistants.
Focuses on experiences of 62 participants using StackSpot AI, highlighting benefits and challenges in software development.
Lacks specific coverage on managing entire codebases, architectural design, training methodologies, and performance metrics.
Explores usability of contextualized AI coding assistants.
Focuses on experiences of 62 participants using StackSpot AI, highlighting benefits and challenges in software development.
Lacks specific coverage on managing entire codebases, architectural design, training methodologies, and performance metrics.
38.8%
2.9
2022
[80] Aligning Offline Metrics and Human Judgments of Value of AI-Pair Programmers
ArXiv
2022 - 8 citations
-
Show abstract
-
Cite
38.8%
topic match
Focuses on aligning offline metrics with human judgments for AI-pair programmers.
Examines the discrepancy between functional correctness metrics and programmer-valued suggestions in AI-driven code generation.
Relevant for understanding performance metrics in coding assistants, but lacks detailed discussion on architectural design and training methodologies.
Focuses on aligning offline metrics with human judgments for AI-pair programmers.
Examines the discrepancy between functional correctness metrics and programmer-valued suggestions in AI-driven code generation.
Relevant for understanding performance metrics in coding assistants, but lacks detailed discussion on architectural design and training methodologies.
36.5%
4.5
2023
[81] Chatbots As Fluent Polyglots: Revisiting Breakthrough Code Snippets
ArXiv
2023 - 8 citations
-
Show abstract
-
Cite
- PDF
36.5%
topic match
Provides AI-driven code assistant insights and improvements on influential code.
Analyzes significant code advances, offering clarity, performance improvements, and deep reasoning for bug corrections and optimizations.
Focuses on automated documentation, code commentary, and translating legacy code, but lacks detail on full pipeline management or architectural designs.
Provides AI-driven code assistant insights and improvements on influential code.
Analyzes significant code advances, offering clarity, performance improvements, and deep reasoning for bug corrections and optimizations.
Focuses on automated documentation, code commentary, and translating legacy code, but lacks detail on full pipeline management or architectural designs.
36.4%
0.0
2023
[82] Role of GenAI in Automated Code Generation within DevOps Practices: Explore how Generative AI
Journal of Knowledge Learning and Science Technology ISSN: 2959-6386 (online)
2023 - 0 citations
-
Show abstract
-
Cite
36.4%
topic match
Discusses AI-driven Automated Code Generation (ACG)
Reviews traditional and AI techniques for ACG, compares performance metrics
Focuses on ACG in DevOps; lacks specifics on generative AI for managing entire codebases
Discusses AI-driven Automated Code Generation (ACG)
Reviews traditional and AI techniques for ACG, compares performance metrics
Focuses on ACG in DevOps; lacks specifics on generative AI for managing entire codebases
36.1%
4.4
2023
[83] On the Reliability and Explainability of Automated Code Generation Approaches
ArXiv
2023 - 8 citations
-
Show abstract
-
Cite
36.1%
topic match
Provides empirical analysis on reliability and explainability of code generation models.
Assesses five models on four datasets, revealing issues in data duplication and input insensitivity.
Relevant by discussing model capabilities but lacks focus on agent-like pipelines or managing entire codebases.
Provides empirical analysis on reliability and explainability of code generation models.
Assesses five models on four datasets, revealing issues in data duplication and input insensitivity.
Relevant by discussing model capabilities but lacks focus on agent-like pipelines or managing entire codebases.
34.7%
6.9
2024
[84] RepairAgent: An Autonomous, LLM-Based Agent for Program Repair
ArXiv
2024 - 4 citations
-
Show abstract
-
Cite
- PDF
34.7%
topic match
Introduces an LLM-based agent for autonomous program repair.
Demonstrates dynamic tool invocation and interaction, managing bug fixes with a flexible, state-guided approach.
Focuses on program repair rather than entire codebase management or architectural design.
Introduces an LLM-based agent for autonomous program repair.
Demonstrates dynamic tool invocation and interaction, managing bug fixes with a flexible, state-guided approach.
Focuses on program repair rather than entire codebase management or architectural design.
33.9%
0.0
2023
[85] Synthesizing Sentience: Integrating Large Language Models and Autonomous Agents for Emulating Human Cognitive Complexity
Journal of Artificial Intelligence, Machine Learning and Data Science
2023 - 0 citations
-
Show abstract
-
Cite
33.9%
topic match
Provides methodology for integrating large language models with autonomous agents.
Explores emulating human cognitive complexity via autonomous agents like GPT-based systems.
Focuses more on cognitive complexity emulation than specifically managing entire codebases or detailed training and performance metrics.
Provides methodology for integrating large language models with autonomous agents.
Explores emulating human cognitive complexity via autonomous agents like GPT-based systems.
Focuses more on cognitive complexity emulation than specifically managing entire codebases or detailed training and performance metrics.
32.8%
6.2
2024
[86] Data Interpreter: An LLM Agent For Data Science
ArXiv
2024 - 4 citations
-
Show abstract
-
Cite
- PDF
32.8%
topic match
Introduces a LLM-based agent for dynamic data science problem-solving.
Uses hierarchical graph structures, tool integration, and logical inconsistency identification for real-time adaptability and optimization.
Focuses on data science with code execution rather than managing entire codebases; lacks emphasis on architectural design, training methodologies, and performance metrics specific to coding assistants.
Introduces a LLM-based agent for dynamic data science problem-solving.
Uses hierarchical graph structures, tool integration, and logical inconsistency identification for real-time adaptability and optimization.
Focuses on data science with code execution rather than managing entire codebases; lacks emphasis on architectural design, training methodologies, and performance metrics specific to coding assistants.
32.0%
17.9
2023
[87] AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors
Journal Not Provided
2023 - 21 citations
-
Show abstract
-
Cite
- PDF
32.0%
topic match
Proposes multi-agent framework leveraging LLMs.
Demonstrates dynamic, collaborative task execution, showcasing emergent social behaviors and strategies for enhancing group efficiency.
Lacks specifics on managing entire codebases or architectural design of coding assistants.
Proposes multi-agent framework leveraging LLMs.
Demonstrates dynamic, collaborative task execution, showcasing emergent social behaviors and strategies for enhancing group efficiency.
Lacks specifics on managing entire codebases or architectural design of coding assistants.
31.8%
0
None
[88] Grounding Code Generation with Input-Output Specifications
Journal Not Provided
None - 0 citations
-
Show abstract
-
Cite
31.8%
topic match
Proposes an approach for instruction fine-tuning LLMs for code generation.
Uses synthetic data and execution-derived feedback to align LLM outputs with user intentions.
Paper focuses on improving initial code generation accuracy, not full management of codebases or broader architectural tasks.
Proposes an approach for instruction fine-tuning LLMs for code generation.
Uses synthetic data and execution-derived feedback to align LLM outputs with user intentions.
Paper focuses on improving initial code generation accuracy, not full management of codebases or broader architectural tasks.
31.1%
87.6
2023
[89] AgentBench: Evaluating LLMs as Agents
ArXiv
2023 - 106 citations
-
Show abstract
-
Cite
- PDF
31.1%
topic match
Provides a benchmark to evaluate LLMs as agents in complex environments.
Assesses reasoning, decision-making, and instruction following in multi-turn settings using 8 distinct environments.
Relevant for understanding LLMs' agent-like capabilities but lacks focus on managing entire codebases and specific coding assistant tasks.
Provides a benchmark to evaluate LLMs as agents in complex environments.
Assesses reasoning, decision-making, and instruction following in multi-turn settings using 8 distinct environments.
Relevant for understanding LLMs' agent-like capabilities but lacks focus on managing entire codebases and specific coding assistant tasks.
30.2%
7.6
2024
[90] RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation
ArXiv
2024 - 5 citations
-
Show abstract
-
Cite
- PDF
30.2%
topic match
Introduces RepoAgent for repository-level code documentation.
RepoAgent uses large language models to proactively generate, maintain, and update code documentation.
Focuses on documentation rather than entire codebase management; relevant for context but not fully aligned with the criteria.
Introduces RepoAgent for repository-level code documentation.
RepoAgent uses large language models to proactively generate, maintain, and update code documentation.
Focuses on documentation rather than entire codebase management; relevant for context but not fully aligned with the criteria.
30.1%
0.0
2024
[91] How to Understand Whole Software Repository?
Journal Not Provided
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
30.1%
topic match
Paper focus: Highlights the need for understanding whole software repositories in ASE.
Detailed insight: Criticizes current LLM-based agents for focusing on local code information, stressing the importance of capturing the global context.
Relevance consideration: Discusses challenges such as long input lengths and complex dependencies but does not detail generative AI for managing entire codebases.
Paper focus: Highlights the need for understanding whole software repositories in ASE.
Detailed insight: Criticizes current LLM-based agents for focusing on local code information, stressing the importance of capturing the global context.
Relevance consideration: Discusses challenges such as long input lengths and complex dependencies but does not detail generative AI for managing entire codebases.
29.9%
9.0
2023
[92] AceCoder: Utilizing Existing Code to Enhance Code Generation
Journal Not Provided
2023 - 14 citations
-
Show abstract
-
Cite
- PDF
29.9%
topic match
Proposes new prompting technique for code generation.
AceCoder uses guided code generation and example retrieval to enhance accuracy.
Focuses on solving requirement understanding and code implementation, but doesn't cover managing entire codebases.
Proposes new prompting technique for code generation.
AceCoder uses guided code generation and example retrieval to enhance accuracy.
Focuses on solving requirement understanding and code implementation, but doesn't cover managing entire codebases.
29.6%
4.4
2023
[93] Large Language Models Are State-of-the-Art Evaluators of Code Generation
ArXiv
2023 - 8 citations
-
Show abstract
-
Cite
29.6%
topic match
Investigates evaluation of code generation by large language models.
Explores limitations of current metrics like BLEU for code tasks.
No direct focus on agent-like pipelines or managing entire codebases.
Investigates evaluation of code generation by large language models.
Explores limitations of current metrics like BLEU for code tasks.
No direct focus on agent-like pipelines or managing entire codebases.
29.0%
24.9
2024
[94] Executable Code Actions Elicit Better LLM Agents
ArXiv
2024 - 18 citations
-
Show abstract
-
Cite
- PDF
29.0%
topic match
Introduces executable Python code for LLM agent actions (CodeAct).
Unifies action space using Python code, improving flexibility and success rates.
Paper tests CodeAct on benchmarks, suggesting higher performance for practical applications and user interactions.
Introduces executable Python code for LLM agent actions (CodeAct).
Unifies action space using Python code, improving flexibility and success rates.
Paper tests CodeAct on benchmarks, suggesting higher performance for practical applications and user interactions.
28.5%
0.0
2023
[95] Static Code Analysis in the AI Era: An In-depth Exploration of the Concept, Function, and Potential of Intelligent Code Analysis Agents
ArXiv
2023 - 0 citations
-
Show abstract
-
Cite
- PDF
28.5%
topic match
Describes the use of AI for intelligent code analysis.
Introduces Intelligent Code Analysis Agent (ICAA) combining LLMs (GPT-3/4) and traditional techniques.
Focus is on error detection and business logic inconsistencies, not on managing entire codebases or architectural design.
Describes the use of AI for intelligent code analysis.
Introduces Intelligent Code Analysis Agent (ICAA) combining LLMs (GPT-3/4) and traditional techniques.
Focus is on error detection and business logic inconsistencies, not on managing entire codebases or architectural design.
27.1%
263.2
2021
[96] Program Synthesis with Large Language Models
ArXiv
2021 - 838 citations
-
Show abstract
-
Cite
- PDF
27.1%
topic match
Evaluates: Uses large language models for program synthesis from natural language descriptions.
Detail: Assesses models on MBPP and MathQA-Python benchmarks in few-shot and fine-tuning regimes.
Relevance: Focuses on code synthesis, not entire codebase management or agent-like pipelines. Lacks architectural and real-world application details.
Evaluates: Uses large language models for program synthesis from natural language descriptions.
Detail: Assesses models on MBPP and MathQA-Python benchmarks in few-shot and fine-tuning regimes.
Relevance: Focuses on code synthesis, not entire codebase management or agent-like pipelines. Lacks architectural and real-world application details.
26.5%
30.0
2023
[97] AutoAgents: A Framework for Automatic Agent Generation
ArXiv
2023 - 32 citations
-
Show abstract
-
Cite
- PDF
26.5%
topic match
25.6%
4.9
2023
[98] Formally Specifying the High-Level Behavior of LLM-Based Agents
ArXiv
2023 - 5 citations
-
Show abstract
-
Cite
- PDF
25.6%
topic match
Proposes a framework for designing LLM-based agents.
Simplifies agent creation by offering a minimalistic generation framework, noting the diversity in agent tasks.
Lacks details on managing codebases, training methodologies, or performance metrics in coding assistants.
Proposes a framework for designing LLM-based agents.
Simplifies agent creation by offering a minimalistic generation framework, noting the diversity in agent tasks.
Lacks details on managing codebases, training methodologies, or performance metrics in coding assistants.
25.0%
64.6
2023
24.3%
1.4
2024
[100] Understanding the Weakness of Large Language Model Agents within a Complex Android Environment
ArXiv
2024 - 1 citations
-
Show abstract
-
Cite
- PDF
24.3%
topic match
Evaluates: LLM agents within general-purpose software systems, including Android environments.
Details: Discusses challenges like vast action spaces, inter-application cooperation, and meeting user constraints.
Relevance: Focuses on broader LLM agent challenges rather than coding assistants managing codebases or specific architectural designs and training methodologies.
Evaluates: LLM agents within general-purpose software systems, including Android environments.
Details: Discusses challenges like vast action spaces, inter-application cooperation, and meeting user constraints.
Relevance: Focuses on broader LLM agent challenges rather than coding assistants managing codebases or specific architectural designs and training methodologies.
24.2%
2.0
2024
[101] A Unified Debugging Approach via LLM-Based Multi-Agent Synergy
ArXiv
2024 - 1 citations
-
Show abstract
-
Cite
- PDF
24.2%
topic match
Proposes an LLM-based multi-agent framework for automated debugging.
Details challenges in LLM-based debugging: fault localization, complex logic errors, and context ignorance.
Does not focus on managing entire codebases, architectural design, or training methodologies.
Proposes an LLM-based multi-agent framework for automated debugging.
Details challenges in LLM-based debugging: fault localization, complex logic errors, and context ignorance.
Does not focus on managing entire codebases, architectural design, or training methodologies.
23.8%
0.0
2024
[102] CodeAgent: Collaborative Agents for Software Engineering
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
23.8%
topic match
Introduces multi-agent-based system for code review.
Details collaborative QA-Checker supervision agent for quality assurance during code review.
Focuses on code review automation, not full codebase management.
Introduces multi-agent-based system for code review.
Details collaborative QA-Checker supervision agent for quality assurance during code review.
Focuses on code review automation, not full codebase management.
23.0%
0.0
2023
[103] of GitHub Copilot’s Code
Journal Not Provided
2023 - 0 citations
-
Show abstract
-
Cite
23.0%
topic match
Scope: Evaluates GitHub Copilot's capabilities.
Details: Assesses code generation, explaining functions, and generating reviews, focusing on developer substitution and software vulnerability.
Relevance: Lacks detailed discussion on training methodologies, overall codebase management, or specific architectural designs.
Scope: Evaluates GitHub Copilot's capabilities.
Details: Assesses code generation, explaining functions, and generating reviews, focusing on developer substitution and software vulnerability.
Relevance: Lacks detailed discussion on training methodologies, overall codebase management, or specific architectural designs.
22.9%
2.4
2023
[104] Human AI Collaboration in Software Engineering: Lessons Learned from a Hands On Workshop
ArXiv
2023 - 2 citations
-
Show abstract
-
Cite
- PDF
22.9%
topic match
Explores human-AI collaboration using ChatGPT in software engineering.
Examines AI's efficiency in code generation and optimization, highlighting human oversight for complex tasks.
Does not focus on managing entire codebases or agent-like pipelines; primarily about collaboration dynamics.
Explores human-AI collaboration using ChatGPT in software engineering.
Examines AI's efficiency in code generation and optimization, highlighting human oversight for complex tasks.
Does not focus on managing entire codebases or agent-like pipelines; primarily about collaboration dynamics.
22.5%
0.0
2023
[105] Automatic Robotic Development through Collaborative Framework by Large Language Models
2023 China Automation Congress (CAC)
2023 - 0 citations
-
Show abstract
-
Cite
- PDF
22.5%
topic match
Proposes a collaborative framework using multiple LLMs for robot development.
Framework involves distinct roles for LLMs: analysts, programmers, testers, enhancing complex task handling.
Focus is on robotic development, not directly on managing entire codebases or coding assistants.
Proposes a collaborative framework using multiple LLMs for robot development.
Framework involves distinct roles for LLMs: analysts, programmers, testers, enhancing complex task handling.
Focus is on robotic development, not directly on managing entire codebases or coding assistants.
22.4%
1.8
2024
[106] Your Co-Workers Matter: Evaluating Collaborative Capabilities of Language Models in Blocks World
ArXiv
2024 - 1 citations
-
Show abstract
-
Cite
- PDF
22.4%
topic match
21.2%
2.5
2022
[107] Generation Probabilities are Not Enough: Improving Error Highlighting for AI Code Suggestions
Journal Not Provided
2022 - 7 citations
-
Show abstract
-
Cite
21.2%
topic match
Evaluates shortcomings in AI code suggestions.
Highlights error-prone recommendations from models like Copilot and their potential introduction of bugs and vulnerabilities.
Does not specifically discuss creating agent-like pipelines or managing entire codebases; focus is on error highlighting in AI code completions.
Evaluates shortcomings in AI code suggestions.
Highlights error-prone recommendations from models like Copilot and their potential introduction of bugs and vulnerabilities.
Does not specifically discuss creating agent-like pipelines or managing entire codebases; focus is on error highlighting in AI code completions.
21.1%
3.0
2023
[108] On the Reliability and Explainability of Language Models for Program Generation
ACM Transactions on Software Engineering and Methodology
2023 - 5 citations
-
Show abstract
-
Cite
- PDF
21.1%
topic match
21.0%
0.0
2022
[109] L EVERAGING N EURAL L ANGUAGE M ODEL FOR A U - TOMATED C ODE Q UALITY I SSUE I DENTIFICATION
Journal Not Provided
2022 - 0 citations
-
Show abstract
-
Cite
21.0%
topic match
What the paper does: Provides a framework for automated code quality issue identification.
Expanded details: Uses neural language models, specifically transformers, to spot and recommend fixes for stylistic and quality issues in code.
Relevance to the topic: Focuses on code quality rather than managing entire codebases; lacks coverage of architectural design, training methodologies, and comprehensive performance metrics for agent-like pipelines.
What the paper does: Provides a framework for automated code quality issue identification.
Expanded details: Uses neural language models, specifically transformers, to spot and recommend fixes for stylistic and quality issues in code.
Relevance to the topic: Focuses on code quality rather than managing entire codebases; lacks coverage of architectural design, training methodologies, and comprehensive performance metrics for agent-like pipelines.
20.4%
0.0
2024
19.8%
27.9
2023
[111] Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization
ArXiv
2023 - 34 citations
-
Show abstract
-
Cite
- PDF
19.8%
topic match
19.6%
0.0
2023
[112] Automated DevOps Pipeline Generation for Code Repositories using Large Language Models
ArXiv
2023 - 0 citations
-
Show abstract
-
Cite
- PDF
19.6%
topic match
19.3%
1.2
2023
19.3%
3.2
2023
[114] Private-Library-Oriented Code Generation with Large Language Models
ArXiv
2023 - 4 citations
-
Show abstract
-
Cite
- PDF
19.3%
topic match
Proposes a framework for generating code in private libraries using LLMs.
Addresses the challenge of LLMs' limited exposure to private APIs during pre-training.
Focuses on code generation rather than managing entire codebases or architectural design.
Proposes a framework for generating code in private libraries using LLMs.
Addresses the challenge of LLMs' limited exposure to private APIs during pre-training.
Focuses on code generation rather than managing entire codebases or architectural design.
19.2%
0.4
2022
[115] Self-Programming Artificial Intelligence Using Code-Generating Language Models
Journal Not Provided
2022 - 1 citations
-
Show abstract
-
Cite
- PDF
19.2%
topic match
Shows application of AI code generation for modifying its own source code.
Details implementation and validation of a self-programming AI model improving itself for better performance.
Does not specifically cover managing entire codebases or detailed performance metrics for coding assistants.
Shows application of AI code generation for modifying its own source code.
Details implementation and validation of a self-programming AI model improving itself for better performance.
Does not specifically cover managing entire codebases or detailed performance metrics for coding assistants.
19.1%
2.1
2024
[116] Generative AI Project Assistant
International Journal of Innovative Science and Research Technology (IJISRT)
2024 - 1 citations
-
Show abstract
-
Cite
19.1%
topic match
Adapts generative AI for project management.
Utilizes NLP and ML for task automation and intelligent suggestions.
Lacks specific focus on coding assistants, codebase management, architectural design, and performance metrics.
Adapts generative AI for project management.
Utilizes NLP and ML for task automation and intelligent suggestions.
Lacks specific focus on coding assistants, codebase management, architectural design, and performance metrics.
18.5%
22.9
2023
[117] Improving ChatGPT Prompt for Code Generation
ArXiv
2023 - 33 citations
-
Show abstract
-
Cite
- PDF
18.5%
topic match
18.4%
3.9
2023
[118] Large Language Models for Code Analysis: Do LLMs Really Do Their Job?
ArXiv
2023 - 4 citations
-
Show abstract
-
Cite
- PDF
18.4%
topic match
18.2%
0.0
2024
[119] Envisioning the Next-Generation AI Coding Assistants: Insights & Proposals
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
18.2%
topic match
Proposes advancements in AI coding assistant design.
Discusses integration with IDEs, backend design, and responsible data collection.
Lacks specific focus on generative AI for agent-like pipelines; relevance is limited.
Proposes advancements in AI coding assistant design.
Discusses integration with IDEs, backend design, and responsible data collection.
Lacks specific focus on generative AI for agent-like pipelines; relevance is limited.
17.3%
7.8
2022
[120] Improving automatically generated code from Codex via Automated Program Repair
ArXiv
2022 - 22 citations
-
Show abstract
-
Cite
17.3%
topic match
17.2%
4.1
2024
[121] NoFunEval: Funny How Code LMs Falter on Requirements Beyond Functional Correctness
ArXiv
2024 - 3 citations
-
Show abstract
-
Cite
- PDF
17.2%
topic match
17.2%
6.4
2023
[122] ML-Bench: Evaluating Large Language Models for Code Generation in Repository-Level Machine Learning Tasks
Journal Not Provided
2023 - 6 citations
-
Show abstract
-
Cite
- PDF
17.2%
topic match
17.1%
0.0
2023
[123] An empirical analysis of GitHub Copilot
Journal Not Provided
2023 - 0 citations
-
Show abstract
-
Cite
17.1%
topic match
Provides an empirical evaluation of GitHub Copilot.
Explores Copilot’s effectiveness and efficiency in aiding software developers with work-related programming tasks.
Lacks detailed discussion on architectural design, training methodologies, or agent-like pipeline management of entire codebases.
Provides an empirical evaluation of GitHub Copilot.
Explores Copilot’s effectiveness and efficiency in aiding software developers with work-related programming tasks.
Lacks detailed discussion on architectural design, training methodologies, or agent-like pipeline management of entire codebases.
16.9%
2.9
2024
[124] Analyzing Prompt Influence on Automated Method Generation: An Empirical Study with Copilot
ArXiv
2024 - 2 citations
-
Show abstract
-
Cite
- PDF
16.9%
topic match
Investigates prompt engineering's effect on code generation with Copilot.
Analyzes how eight prompt features impact correctness, complexity, size, and similarity of generated Java methods.
Does not address agent-like pipelines or entire codebase management. Focuses more on improving individual code generation instances.
Investigates prompt engineering's effect on code generation with Copilot.
Analyzes how eight prompt features impact correctness, complexity, size, and similarity of generated Java methods.
Does not address agent-like pipelines or entire codebase management. Focuses more on improving individual code generation instances.
16.9%
0.0
2024
[125] CodeCloak: A Method for Evaluating and Mitigating Code Leakage by LLM Code Assistants
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
16.9%
topic match
What the paper does:
Evaluates and mitigates code leakage by LLM code assistants.
What the paper does:
Evaluates and mitigates code leakage by LLM code assistants.
16.6%
0.0
2023
[126] GPT-in-the-Loop: Supporting Adaptation in Multiagent Systems
2023 IEEE International Conference on Big Data (BigData)
2023 - 0 citations
-
Show abstract
-
Cite
16.6%
topic match
Shows potential of GPT-driven behavior in multiagent systems.
Demonstrates enhanced decision-making and adaptability using GPT-4 within an IoT framework.
Focuses on multiagent systems, not specifically on entire codebase management or detailed coding assistant metrics.
Shows potential of GPT-driven behavior in multiagent systems.
Demonstrates enhanced decision-making and adaptability using GPT-4 within an IoT framework.
Focuses on multiagent systems, not specifically on entire codebase management or detailed coding assistant metrics.
16.6%
0.0
2024
[127] Benchmarking Large Language Models for Code Generation
International Journal For Multidisciplinary Research
2024 - 0 citations
-
Show abstract
-
Cite
16.6%
topic match
Provides performance benchmarks for LLMs in code generation.
Focuses on evaluating LLMs like codellama-13b-instruct for interpreting and generating code from natural language instructions.
Does not specifically address agent-like pipelines, entire codebase management, or detailed architectural design and training methodologies.
Provides performance benchmarks for LLMs in code generation.
Focuses on evaluating LLMs like codellama-13b-instruct for interpreting and generating code from natural language instructions.
Does not specifically address agent-like pipelines, entire codebase management, or detailed architectural design and training methodologies.
16.6%
24.8
2022
[128] Automated Repair of Programs from Large Language Models
2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE)
2022 - 60 citations
-
Show abstract
-
Cite
- PDF
16.6%
topic match
16.5%
0.6
2023
16.4%
0.0
2023
[130] Automatic Unit Test Data Generation and Actor-Critic Reinforcement Learning for Code Synthesis
ArXiv
2023 - 0 citations
-
Show abstract
-
Cite
- PDF
16.4%
topic match
16.3%
74.8
2023
[131] Is ChatGPT the Ultimate Programming Assistant - How far is it?
ArXiv
2023 - 112 citations
-
Show abstract
-
Cite
- PDF
16.3%
topic match
16.1%
28.6
2023
[132] Evaluating the Code Quality of AI-Assisted Code Generation Tools: An Empirical Study on GitHub Copilot, Amazon CodeWhisperer, and ChatGPT
ArXiv
2023 - 43 citations
-
Show abstract
-
Cite
- PDF
16.1%
topic match
16.0%
4.1
2024
[133] An Empirical Study on Usage and Perceptions of LLMs in a Software Engineering Project
ArXiv
2024 - 3 citations
-
Show abstract
-
Cite
- PDF
16.0%
topic match
15.9%
0.0
2024
[134] Enhancing Programming Error Messages in Real Time with Generative AI
https://doi.org/10.1145/3613905.3647967
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
15.9%
topic match
Shows generative AI enhancing programming error messages.
Implements GPT-4 in an automated assessment tool for real-time compiler, run-time, and logic errors.
Lacks coverage of managing entire codebases, architectural design, or performance metrics for coding assistants.
Shows generative AI enhancing programming error messages.
Implements GPT-4 in an automated assessment tool for real-time compiler, run-time, and logic errors.
Lacks coverage of managing entire codebases, architectural design, or performance metrics for coding assistants.
15.0%
0.0
2024
[135] Integrating Generative AI for Advancing Agile Software Development and Mitigating Project Management Challenges
International Journal of Advanced Computer Science and Applications
2024 - 0 citations
-
Show abstract
-
Cite
15.0%
topic match
Explores integrating Generative AI in Agile software development.
Focuses on using Generative AI for code generation, automated testing, and predictive analytics within Agile methodologies.
Lacks specific coverage on managing entire codebases, agent-like pipelines, architectural design, training methodologies, and detailed performance metrics.
Explores integrating Generative AI in Agile software development.
Focuses on using Generative AI for code generation, automated testing, and predictive analytics within Agile methodologies.
Lacks specific coverage on managing entire codebases, agent-like pipelines, architectural design, training methodologies, and detailed performance metrics.
14.8%
0.0
2024
[136] How far are AI-powered programming assistants from meeting developers' needs?
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
14.8%
topic match
14.4%
6.5
2024
[137] RepoHyper: Better Context Retrieval Is All You Need for Repository-Level Code Completion
ArXiv
2024 - 4 citations
-
Show abstract
-
Cite
- PDF
14.4%
topic match
13.9%
0.6
2023
[138] Accelerating software development with AI: exploring the impact of ChatGPT and GitHub Copilot
CTE
2023 - 1 citations
-
Show abstract
-
Cite
13.9%
topic match
13.4%
40.1
2023
[139] ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation
ArXiv
2023 - 49 citations
-
Show abstract
-
Cite
- PDF
13.4%
topic match
13.4%
0.0
2024
[140] InfiCoder-Eval: Systematically Evaluating the Question-Answering Capabilities of Code Large Language Models
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
13.4%
topic match
13.3%
0.0
2023
12.9%
23.7
2023
12.6%
3.1
2023
[143] Exploring and Characterizing Large Language Models For Embedded System Development and Debugging
ArXiv
2023 - 4 citations
-
Show abstract
-
Cite
- PDF
12.6%
topic match
12.6%
509.9
2023
[144] Toolformer: Language Models Can Teach Themselves to Use Tools
ArXiv
2023 - 867 citations
-
Show abstract
-
Cite
- PDF
12.6%
topic match
12.5%
6.4
2023
[145] CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation
ArXiv
2023 - 6 citations
-
Show abstract
-
Cite
- PDF
12.5%
topic match
12.3%
1.9
2023
[146] The Program Testing Ability of Large Language Models for Code
ArXiv
2023 - 2 citations
-
Show abstract
-
Cite
- PDF
12.3%
topic match
12.1%
2.0
2024
[147] Class-Level Code Generation from Natural Language Using Iterative, Tool-Enhanced Reasoning over Repository
Journal Not Provided
2024 - 1 citations
-
Show abstract
-
Cite
- PDF
12.1%
topic match
12.1%
12.0
2023
11.5%
0.0
2023
11.5%
4.4
2023
[150] CodeApex: A Bilingual Programming Evaluation Benchmark for Large Language Models
ArXiv
2023 - 5 citations
-
Show abstract
-
Cite
- PDF
11.5%
topic match
11.2%
9.9
2023
[151] TPTU: Large Language Model-based AI Agents for Task Planning and Tool Usage
Journal Not Provided
2023 - 12 citations
-
Show abstract
-
Cite
- PDF
11.2%
topic match
11.1%
225.2
2023
[152] StarCoder: may the source be with you!
ArXiv
2023 - 328 citations
-
Show abstract
-
Cite
- PDF
11.1%
topic match
11.0%
1.1
2023
[153] Evaluating the Usability and Functionality of Intelligent Source Code Completion Assistants: A Comprehensive Review
Applied Sciences
2023 - 1 citations
-
Show abstract
-
Cite
11.0%
topic match
10.8%
61.3
2022
[154] An Empirical Evaluation of GitHub Copilot's Code Suggestions
2022 IEEE/ACM 19th International Conference on Mining Software Repositories (MSR)
2022 - 152 citations
-
Show abstract
-
Cite
10.8%
topic match
10.6%
1.5
2024
[155] Assessing AI-Based Code Assistants in Method Generation Tasks
ArXiv
2024 - 1 citations
-
Show abstract
-
Cite
- PDF
10.6%
topic match
10.5%
13.6
2023
[156] CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules
ArXiv
2023 - 14 citations
-
Show abstract
-
Cite
- PDF
10.5%
topic match
10.4%
2.0
2023
[157] ChatGPT as a Software Development Bot: A Project-Based Study
International Conference on Evaluation of Novel Approaches to Software Engineering
2023 - 2 citations
-
Show abstract
-
Cite
- PDF
10.4%
topic match
Shows use of ChatGPT as a supportive tool in software development.
Enhances productivity, accuracy, learning outcomes, and collaboration among students.
Focuses on educational impact, with limited details on managing entire codebases or agent-like pipelines.
Shows use of ChatGPT as a supportive tool in software development.
Enhances productivity, accuracy, learning outcomes, and collaboration among students.
Focuses on educational impact, with limited details on managing entire codebases or agent-like pipelines.
10.2%
0.0
2024
[158] Experimenting with Multi-Agent Software Development: Towards a Unified Platform
Journal Not Provided
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
10.2%
topic match
10.1%
0.0
2023
[159] Are We Testing or Being Tested? Exploring the Practical Applications of Large Language Models in Software Testing
ArXiv
2023 - 0 citations
-
Show abstract
-
Cite
- PDF
10.1%
topic match
9.9%
0.0
2024
[160] Using AI Assistants in Software Development: A Qualitative Study on Security Practices and Concerns
Journal Not Provided
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
9.9%
topic match
9.8%
2.5
2024
[161] LLM4PLC: Harnessing Large Language Models for Verifiable Programming of PLCs in Industrial Control Systems
ArXiv
2024 - 2 citations
-
Show abstract
-
Cite
- PDF
9.8%
topic match
9.8%
0.0
2024
[162] Large Language Models Synergize with Automated Machine Learning
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
9.8%
topic match
9.7%
146.0
2023
[163] CodeT5+: Open Code Large Language Models for Code Understanding and Generation
Conference on Empirical Methods in Natural Language Processing
2023 - 211 citations
-
Show abstract
-
Cite
- PDF
9.7%
topic match
9.7%
7.2
2024
[164] Large Language Model Evaluation Via Multi AI Agents: Preliminary results
ArXiv
2024 - 4 citations
-
Show abstract
-
Cite
- PDF
9.7%
topic match
9.5%
1.6
2024
[165] Transforming Competition into Collaboration: The Revolutionary Role of Multi-Agent Systems and Language Models in Modern Organizations
ArXiv
2024 - 1 citations
-
Show abstract
-
Cite
- PDF
9.5%
topic match
9.4%
0
None
[166] A Good Novelist Should be a Good Coder: From Language Critics to Automatic Code Generation
Journal Not Provided
None - 0 citations
-
Show abstract
-
Cite
9.4%
topic match
9.4%
14.9
2023
[167] ChatGPT: A Study on its Utility for Ubiquitous Software Engineering Tasks
ArXiv
2023 - 21 citations
-
Show abstract
-
Cite
- PDF
9.4%
topic match
9.3%
3.8
2023
[168] Exploring the Robustness of Large Language Models for Solving Programming Problems
ArXiv
2023 - 5 citations
-
Show abstract
-
Cite
- PDF
9.3%
topic match
9.2%
9.7
2023
[169] A Preliminary Analysis on the Code Generation Capabilities of GPT-3.5 and Bard AI Models for Java Functions
ArXiv
2023 - 14 citations
-
Show abstract
-
Cite
- PDF
9.2%
topic match
9.1%
0.0
2023
[170] Integrating Cloud-Based AI in Software Engineers' Professional Training and Development
2023 IEEE Frontiers in Education Conference (FIE)
2023 - 0 citations
-
Show abstract
-
Cite
9.1%
topic match
8.9%
14.5
2022
[171] Better Together? An Evaluation of AI-Supported Code Translation
27th International Conference on Intelligent User Interfaces
2022 - 39 citations
-
Show abstract
-
Cite
- PDF
8.9%
topic match
8.7%
0.0
2024
[172] Large Language Models as Test Case Generators: Performance Evaluation and Enhancement
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
8.7%
topic match
8.7%
0.0
2023
[173] Code generation for large commercial projects: how commercial development will look like in the future
Connectivity
2023 - 0 citations
-
Show abstract
-
Cite
8.7%
topic match
8.6%
0.0
2022
[174] An Initial Look at Self-Reprogramming Artificial Intelligence
ArXiv
2022 - 0 citations
-
Show abstract
-
Cite
8.6%
topic match
8.4%
1.1
2023
[175] Lessons from Building StackSpot AI: A Contextualized AI Coding Assistant
https://doi.org/10.1145/3639477.3639751
2023 - 1 citations
-
Show abstract
-
Cite
- PDF
8.4%
topic match
8.3%
13.7
2024
[176] LDB: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step
Journal Not Provided
2024 - 9 citations
-
Show abstract
-
Cite
- PDF
8.3%
topic match
8.3%
17.1
2022
8.3%
23.1
2022
[178] PanGu-Coder: Program Synthesis with Function-Level Language Modeling
ArXiv
2022 - 52 citations
-
Show abstract
-
Cite
- PDF
8.3%
topic match
8.2%
3.0
2024
[179] Can ChatGPT Support Developers? An Empirical Evaluation of Large Language Models for Code Generation
ArXiv
2024 - 2 citations
-
Show abstract
-
Cite
- PDF
8.2%
topic match
8.2%
37.6
2022
[180] Few-shot training LLMs for project-specific code-summarization
Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering
2022 - 86 citations
-
Show abstract
-
Cite
- PDF
8.2%
topic match
8.0%
1.7
2024
[181] Towards Single-System Illusion in Software-Defined Vehicles - Automated, AI-Powered Workflow
ArXiv
2024 - 1 citations
-
Show abstract
-
Cite
- PDF
8.0%
topic match
7.9%
27.6
2022
7.8%
0.0
2024
[183] Reasoning Capacity in Multi-Agent Systems: Limitations, Challenges and Human-Centered Solutions
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
7.8%
topic match
7.7%
0.0
2024
[184] Rocks Coding, Not Development-A Human-Centric, Experimental Evaluation of LLM-Supported SE Tasks
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
7.7%
topic match
7.7%
0.0
2023
[185] EXPLORING THE DESIGN SPACE OF AI BASED CODE COMPLETION ENGINES
Journal Not Provided
2023 - 0 citations
-
Show abstract
-
Cite
7.7%
topic match
7.5%
0.7
2023
[186] LMs: Understanding Code Syntax and Semantics for Code Analysis
Journal Not Provided
2023 - 1 citations
-
Show abstract
-
Cite
- PDF
7.5%
topic match
7.3%
24.6
2022
[187] What is it like to program with artificial intelligence?
Annual Workshop of the Psychology of Programming Interest Group
2022 - 54 citations
-
Show abstract
-
Cite
- PDF
7.3%
topic match
7.3%
0.0
2024
[188] TESTEVAL: Benchmarking Large Language Models for Test Case Generation
Journal Not Provided
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
7.3%
topic match
7.2%
8.4
2023
[189] Think Outside the Code: Brainstorming Boosts Large Language Models in Code Generation
ArXiv
2023 - 12 citations
-
Show abstract
-
Cite
- PDF
7.2%
topic match
7.1%
160.6
2023
[190] Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation
ArXiv
2023 - 237 citations
-
Show abstract
-
Cite
- PDF
7.1%
topic match
7.1%
0.0
2024
[191] Codexity: Secure AI-assisted Code Generation
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
7.1%
topic match
7.0%
5.4
2024
[192] Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization
ArXiv
2024 - 3 citations
-
Show abstract
-
Cite
- PDF
7.0%
topic match
7.0%
2.4
2023
[193] MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks
ArXiv
2023 - 2 citations
-
Show abstract
-
Cite
- PDF
7.0%
topic match
6.8%
0.0
2023
[194] Deep Learning Based Code Generation Methods: Literature Review
https://doi.org/10.13328/j.cnki.jos.006981.
2023 - 0 citations
-
Show abstract
-
Cite
- PDF
6.8%
topic match
6.8%
4.0
2024
[195] Can Large Language Models Write Parallel Code?
ArXiv
2024 - 3 citations
-
Show abstract
-
Cite
- PDF
6.8%
topic match
6.8%
23.8
2021
[196] In-IDE Code Generation from Natural Language: Promise and Challenges
ACM Transactions on Software Engineering and Methodology (TOSEM)
2021 - 89 citations
-
Show abstract
-
Cite
- PDF
6.8%
topic match
6.7%
7.5
2024
[197] Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments
ArXiv
2024 - 5 citations
-
Show abstract
-
Cite
- PDF
6.7%
topic match
6.7%
8.3
2024
[198] StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback
ArXiv
2024 - 6 citations
-
Show abstract
-
Cite
- PDF
6.7%
topic match
6.6%
5.0
2024
[199] LLM Harmony: Multi-Agent Communication for Problem Solving
ArXiv
2024 - 4 citations
-
Show abstract
-
Cite
- PDF
6.6%
topic match
6.6%
0.0
2023
[200] A Novel Approach for Rapid Development Based on ChatGPT and Prompt Engineering
ArXiv
2023 - 0 citations
-
Show abstract
-
Cite
- PDF
6.6%
topic match
6.6%
1.0
2019
6.6%
0.0
2024
[202] Divide-and-Conquer Meets Consensus: Unleashing the Power of Functions in Code Generation
Journal Not Provided
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
6.6%
topic match
6.5%
63.7
2023
[203] LEVER: Learning to Verify Language-to-Code Generation with Execution
ArXiv
2023 - 107 citations
-
Show abstract
-
Cite
- PDF
6.5%
topic match
6.4%
8.9
2023
[204] A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and Challenges
International Conference on Software Engineering
2023 - 14 citations
-
Show abstract
-
Cite
- PDF
6.4%
topic match
6.4%
0.0
2024
[205] CONLINE: Complex Code Generation and Refinement with Online Searching and Correctness Testing
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
6.4%
topic match
6.4%
0.0
2024
[206] Generative Software Engineering
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
6.4%
topic match
6.3%
4.5
2023
6.3%
0.0
2023
[208] Students' Perspective on AI Code Completion: Benefits and Challenges
ArXiv
2023 - 0 citations
-
Show abstract
-
Cite
- PDF
6.3%
topic match
6.3%
8.9
2022
[209] Security Implications of Large Language Model Code Assistants: A User Study
ArXiv
2022 - 25 citations
-
Show abstract
-
Cite
6.3%
topic match
6.3%
2.9
2023
[210] Generative AI for Product Design: Getting the Right Design and the Design Right
ArXiv
2023 - 4 citations
-
Show abstract
-
Cite
- PDF
6.3%
topic match
6.2%
62.2
2022
[211] CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning
ArXiv
2022 - 143 citations
-
Show abstract
-
Cite
- PDF
6.2%
topic match
6.2%
0.0
2024
[212] Content-Centric Prototyping of Generative AI Applications: Emerging Approaches and Challenges in Collaborative Software Teams
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
6.2%
topic match
6.2%
0.0
2023
6.1%
7.4
2024
[214] AutoCodeRover: Autonomous Program Improvement
ArXiv
2024 - 4 citations
-
Show abstract
-
Cite
- PDF
6.1%
topic match
6.1%
19.9
2023
[215] Magicoder: Source Code Is All You Need
ArXiv
2023 - 36 citations
-
Show abstract
-
Cite
6.1%
topic match
6.1%
12.9
2022
[216] AI-Driven Development Is Here: Should You Worry?
IEEE Software
2022 - 34 citations
-
Show abstract
-
Cite
- PDF
6.1%
topic match
6.1%
0.0
2023
[217] Stochastic Code Generation
ArXiv
2023 - 0 citations
-
Show abstract
-
Cite
- PDF
6.1%
topic match
6.1%
13.4
2023
[218] Experiential Co-Learning of Software-Developing Agents
ArXiv
2023 - 11 citations
-
Show abstract
-
Cite
- PDF
6.1%
topic match
6.1%
1.1
2023
[219] A Review on Code Generation with LLMs: Application and Evaluation
2023 IEEE International Conference on Medical Artificial Intelligence (MedAI)
2023 - 1 citations
-
Show abstract
-
Cite
6.1%
topic match
6.0%
7.7
2024
[220] Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization
ArXiv
2024 - 5 citations
-
Show abstract
-
Cite
- PDF
6.0%
topic match
6.0%
217.5
2022
[221] CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis
International Conference on Learning Representations
2022 - 561 citations
-
Show abstract
-
Cite
- PDF
6.0%
topic match
6.0%
31.4
2022
5.9%
6.1
2023
[223] STEAM: Simulating the InTeractive BEhavior of ProgrAMmers for Automatic Bug Fixing
ArXiv
2023 - 7 citations
-
Show abstract
-
Cite
- PDF
5.9%
topic match
5.9%
2.2
2023
[224] Improving Code Generation by Dynamic Temperature Sampling
ArXiv
2023 - 4 citations
-
Show abstract
-
Cite
5.9%
topic match
5.9%
0
None
5.9%
0.0
2023
5.8%
8.1
2018
[227] Context-Aware Conversational Developer Assistants
2018 IEEE/ACM 40th International Conference on Software Engineering (ICSE)
2018 - 52 citations
-
Show abstract
-
Cite
5.8%
topic match
5.8%
100.9
2023
[228] CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Evaluations on HumanEval-X
ArXiv
2023 - 158 citations
-
Show abstract
-
Cite
- PDF
5.8%
topic match
5.8%
114.9
2023
[229] Language Models can Solve Computer Tasks
ArXiv
2023 - 180 citations
-
Show abstract
-
Cite
- PDF
5.8%
topic match
5.7%
2.9
2024
[230] Framework for evaluating code generation ability of large language models
ETRI Journal
2024 - 2 citations
-
Show abstract
-
Cite
5.7%
topic match
5.7%
5.7
2022
[231] A Scalable and Extensible Approach to Benchmarking NL2Code for 18 Programming Languages
ArXiv
2022 - 16 citations
-
Show abstract
-
Cite
5.7%
topic match
5.7%
0.0
2022
[232] Autonomous Intelligent Software Development
ArXiv
2022 - 0 citations
-
Show abstract
-
Cite
- PDF
5.7%
topic match
5.6%
0.0
2022
[233] Automated Repair of Code from Language Models
Journal Not Provided
2022 - 0 citations
-
Show abstract
-
Cite
5.6%
topic match
5.6%
13.3
2022
[234] MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation
Journal Not Provided
2022 - 29 citations
-
Show abstract
-
Cite
- PDF
5.6%
topic match
5.6%
16.2
2023
[235] Can LLM Replace Stack Overflow? A Study on Robustness and Reliability of Large Language Model Code Generation
AAAI Conference on Artificial Intelligence
2023 - 19 citations
-
Show abstract
-
Cite
- PDF
5.6%
topic match
5.6%
0.0
2024
[236] CodeEditorBench: Evaluating Code Editing Capability of Large Language Models
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
5.6%
topic match
5.6%
1.1
2023
[237] Function-constrained Program Synthesis
ArXiv
2023 - 1 citations
-
Show abstract
-
Cite
- PDF
5.6%
topic match
5.6%
6.3
2023
5.5%
1.5
2022
5.5%
35.5
2023
[240] Self-Edit: Fault-Aware Code Editor for Code Generation
Annual Meeting of the Association for Computational Linguistics
2023 - 52 citations
-
Show abstract
-
Cite
- PDF
5.5%
topic match
5.4%
1.0
2023
[241] GPTutor: an open-source AI pair programming tool alternative to Copilot
ArXiv
2023 - 1 citations
-
Show abstract
-
Cite
- PDF
5.4%
topic match
5.4%
2.6
2024
[242] LangProp: A code optimization framework using Large Language Models applied to driving
Journal Not Provided
2024 - 2 citations
-
Show abstract
-
Cite
- PDF
5.4%
topic match
5.4%
1.3
2024
[243] PythonSaga: Redefining the Benchmark to Evaluate Code Generating LLM
Journal Not Provided
2024 - 1 citations
-
Show abstract
-
Cite
- PDF
5.4%
topic match
5.4%
0.0
2023
[244] The Ethics of Artificial Intelligence in the Era of Generative AI
Journal of Systemics, Cybernetics and Informatics
2023 - 0 citations
-
Show abstract
-
Cite
5.4%
topic match
5.4%
0.0
2024
[245] Assessing the Effectiveness and Security Implications of AI Code Generators
Journal of The Colloquium for Information Systems Security Education
2024 - 0 citations
-
Show abstract
-
Cite
5.4%
topic match
5.3%
0.0
2024
[246] Advancing GenAI Assisted Programming-A Comparative Study on Prompt Efficiency and Code Quality Between GPT-4 and GLM-4
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
5.3%
topic match
5.3%
7.4
2023
[247] Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation
International Conference on Machine Learning
2023 - 11 citations
-
Show abstract
-
Cite
- PDF
5.3%
topic match
5.3%
25.3
2023
[248] RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems
ArXiv
2023 - 35 citations
-
Show abstract
-
Cite
- PDF
5.3%
topic match
5.3%
41.9
2023
5.3%
61.4
2023
[250] AgentTuning: Enabling Generalized Agent Abilities for LLMs
ArXiv
2023 - 62 citations
-
Show abstract
-
Cite
- PDF
5.3%
topic match
5.2%
1.7
2024
[251] Enhancing Security of AI-Based Code Synthesis with GitHub Copilot via Cheap and Efficient Prompt-Engineering
ArXiv
2024 - 1 citations
-
Show abstract
-
Cite
- PDF
5.2%
topic match
5.2%
1.5
2023
[252] Validating AI-Generated Code with Live Programming
International Conference on Human Factors in Computing Systems
2023 - 2 citations
-
Show abstract
-
Cite
- PDF
5.2%
topic match
5.2%
66.1
2022
[253] GitHub Copilot AI pair programmer: Asset or Liability?
J. Syst. Softw.
2022 - 153 citations
-
Show abstract
-
Cite
- PDF
5.2%
topic match
5.2%
1.4
2024
[254] LLMs for Coding and Robotics Education
ArXiv
2024 - 1 citations
-
Show abstract
-
Cite
- PDF
5.2%
topic match
5.2%
0.8
2020
[255] Automated Coding: The Quest to Develop Programs That Write Programs
Computer
2020 - 4 citations
-
Show abstract
-
Cite
5.2%
topic match
5.2%
0.0
2024
[256] On Augmenting Scenario-Based Modeling with Generative AI
International Conference on Model-Driven Engineering and Software Development
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
5.2%
topic match
5.2%
0.0
2024
[257] Transforming Software Development with Generative AI: Empirical Insights on Collaboration and Workflow
Journal Not Provided
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
5.2%
topic match
5.1%
7.5
2023
[258] Practices and Challenges of Using GitHub Copilot: An Empirical Study
International Conference on Software Engineering and Knowledge Engineering
2023 - 12 citations
-
Show abstract
-
Cite
- PDF
5.1%
topic match
5.1%
7.8
2024
[259] Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering
ArXiv
2024 - 6 citations
-
Show abstract
-
Cite
- PDF
5.1%
topic match
5.1%
5.2
2024
[260] CYCLE: Learning to Self-Refine the Code Generation
ArXiv
2024 - 3 citations
-
Show abstract
-
Cite
- PDF
5.1%
topic match
5.0%
29.9
2023
[261] TPTU: Task Planning and Tool Usage of Large Language Model-based AI Agents
ArXiv
2023 - 54 citations
-
Show abstract
-
Cite
5.0%
topic match
5.0%
35.1
2023
4.9%
2.7
2023
[263] Demystifying Practices, Challenges and Expected Features of Using GitHub Copilot
ArXiv
2023 - 3 citations
-
Show abstract
-
Cite
- PDF
4.9%
topic match
4.9%
0.0
2024
[264] On the Limitations of Embedding Based Methods for Measuring Functional Correctness for Code Generation
Journal Not Provided
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
4.9%
topic match
4.9%
0.0
2023
[265] AI-driven software engineering
Advances in Engineering Innovation
2023 - 0 citations
-
Show abstract
-
Cite
4.9%
topic match
4.9%
0.0
2024
[266] Low-Cost Language Models: Survey and Performance Evaluation on Python Code Generation
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
4.9%
topic match
4.9%
195.2
2023
[267] ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
ArXiv
2023 - 240 citations
-
Show abstract
-
Cite
- PDF
4.9%
topic match
4.9%
0.0
2023
4.8%
1.5
2024
[269] AgentScope: A Flexible yet Robust Multi-Agent Platform
ArXiv
2024 - 1 citations
-
Show abstract
-
Cite
- PDF
4.8%
topic match
4.8%
15.1
2024
[270] Evaluating Large Language Models in Class-Level Code Generation
International Conference on Software Engineering
2024 - 8 citations
-
Show abstract
-
Cite
4.8%
topic match
4.8%
36.2
2023
[271] Agents: An Open-source Framework for Autonomous Language Agents
ArXiv
2023 - 40 citations
-
Show abstract
-
Cite
- PDF
4.8%
topic match
4.8%
0.0
2024
[272] An Approach for Rapid Source Code Development Based on ChatGPT and Prompt Engineering
IEEE Access
2024 - 0 citations
-
Show abstract
-
Cite
4.8%
topic match
4.8%
7.0
2024
[273] EffiBench: Benchmarking the Efficiency of Automatically Generated Code
ArXiv
2024 - 5 citations
-
Show abstract
-
Cite
- PDF
4.8%
topic match
4.8%
1.7
2024
[274] Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback
ArXiv
2024 - 1 citations
-
Show abstract
-
Cite
- PDF
4.8%
topic match
4.8%
12.7
2024
[275] AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls
ArXiv
2024 - 9 citations
-
Show abstract
-
Cite
- PDF
4.8%
topic match
4.8%
1.4
2023
4.7%
0.0
2024
[277] A Survey on Large Language Models for Code Generation
Journal Not Provided
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
4.7%
topic match
4.7%
13.3
2023
4.7%
82.9
2022
[279] CodeT: Code Generation with Generated Tests
ArXiv
2022 - 187 citations
-
Show abstract
-
Cite
- PDF
4.7%
topic match
4.6%
0.0
2024
[280] Prioritizing Software Requirements Using Large Language Models
Journal Not Provided
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
4.6%
topic match
4.6%
78.6
2022
4.6%
1.7
2023
4.6%
0.0
2024
4.6%
1.7
2024
[284] AUTONODE: A Neuro-Graphic Self-Learnable Engine for Cognitive GUI Automation
ArXiv
2024 - 1 citations
-
Show abstract
-
Cite
- PDF
4.6%
topic match
4.6%
0.0
2024
[285] The Impact of AI Tool on Engineering at ANZ Bank An Emperical Study on GitHub Copilot within Coporate Environment
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
4.6%
topic match
4.5%
2.2
2024
[286] Benchmarking Educational Program Repair
Journal Not Provided
2024 - 1 citations
-
Show abstract
-
Cite
- PDF
4.5%
topic match
4.5%
0.0
2024
[287] A systematic evaluation of large language models for generating programming code
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
4.5%
topic match
4.5%
1.1
2023
[288] Best uses of ChatGPT and Generative AI for computer science research
ArXiv
2023 - 1 citations
-
Show abstract
-
Cite
- PDF
4.5%
topic match
4.5%
12.1
2021
[289] Can OpenAI Codex and Other Large Language Models Help Us Fix Security Bugs?
ArXiv
2021 - 46 citations
-
Show abstract
-
Cite
4.5%
topic match
4.4%
17.9
2024
[290] LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
ArXiv
2024 - 11 citations
-
Show abstract
-
Cite
- PDF
4.4%
topic match
4.4%
0.0
2024
[291] Are Human Rules Necessary? Generating Reusable APIs with CoT Reasoning and In-Context Learning
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
4.4%
topic match
4.4%
847.1
2021
[292] Evaluating Large Language Models Trained on Code
ArXiv
2021 - 2790 citations
-
Show abstract
-
Cite
- PDF
4.4%
topic match
4.4%
5.0
2024
[293] Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
J. Assoc. Inf. Syst.
2024 - 4 citations
-
Show abstract
-
Cite
4.4%
topic match
4.3%
2.5
2024
[294] Effectiveness of ChatGPT in Coding: A Comparative Analysis of Popular Large Language Models
Digit.
2024 - 2 citations
-
Show abstract
-
Cite
4.3%
topic match
4.3%
0.6
2017
[295] Automatic Code Completion
Journal Not Provided
2017 - 5 citations
-
Show abstract
-
Cite
4.3%
topic match
4.3%
5.8
2023
[296] A Comparative Study of Code Generation using ChatGPT 3.5 across 10 Programming Languages
ArXiv
2023 - 7 citations
-
Show abstract
-
Cite
- PDF
4.3%
topic match
4.3%
15.8
2023
[297] Natural Language Generation and Understanding of Big Code for AI-Assisted Programming: A Review
Entropy
2023 - 22 citations
-
Show abstract
-
Cite
- PDF
4.3%
topic match
4.2%
1.8
2023
4.2%
2.0
2023
[299] ChatGPT opens a new door for bioinformatics
Quantitative biology (Beijing, China)
2023 - 3 citations
-
Show abstract
-
Cite
4.2%
topic match
4.2%
1.9
2023
[300] Test-Case-Driven Programming Understanding in Large Language Models for Better Code Generation
ArXiv
2023 - 2 citations
-
Show abstract
-
Cite
- PDF
4.2%
topic match
4.2%
0.0
2024
[301] Contextual API Completion for Unseen Repositories Using LLMs
Journal Not Provided
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
4.2%
topic match
4.1%
1.0
2023
[302] Coding by Design: GPT-4 empowers Agile Model Driven Development
ArXiv
2023 - 1 citations
-
Show abstract
-
Cite
- PDF
4.1%
topic match
4.1%
0.0
2023
[303] Safurai 001: New Qualitative Approach for Code LLM Evaluation
ArXiv
2023 - 0 citations
-
Show abstract
-
Cite
- PDF
4.1%
topic match
4.1%
7.2
2023
[304] Analysis of ChatGPT on Source Code
ArXiv
2023 - 10 citations
-
Show abstract
-
Cite
- PDF
4.1%
topic match
4.1%
0.0
2024
[305] A STUDY ON THE APPLICATION OF GEN AI TOOLS SUPPORTS TO FINANCIAL SERVICES
INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT
2024 - 0 citations
-
Show abstract
-
Cite
4.1%
topic match
4.1%
4.2
2024
[306] S-Agents: Self-organizing Agents in Open-ended Environments
ArXiv
2024 - 3 citations
-
Show abstract
-
Cite
- PDF
4.1%
topic match
4.0%
1.1
2023
[307] Assessing the Security of GitHub Copilot Generated Code - A Targeted Replication Study
ArXiv
2023 - 1 citations
-
Show abstract
-
Cite
- PDF
4.0%
topic match
4.0%
1.8
2024
[308] Exploring Autonomous Agents through the Lens of Large Language Models: A Review
ArXiv
2024 - 1 citations
-
Show abstract
-
Cite
- PDF
4.0%
topic match
4.0%
49.6
2023
[309] Emergent autonomous scientific research capabilities of large language models
ArXiv
2023 - 76 citations
-
Show abstract
-
Cite
- PDF
4.0%
topic match
4.0%
13.7
2022
[310] Compilable Neural Code Generation with Compiler Feedback
Findings
2022 - 36 citations
-
Show abstract
-
Cite
- PDF
4.0%
topic match
4.0%
None
None
[311] Generative AI in Introductory Programming
Journal Not Provided
None - 1 citations
-
Show abstract
-
Cite
4.0%
topic match
4.0%
7.2
2023
[312] Do Large Language Models Pay Similar Attention Like Human Programmers When Generating Code?
https://doi.org/10.1145/3660807
2023 - 10 citations
-
Show abstract
-
Cite
- PDF
4.0%
topic match
4.0%
36.0
2021
[313] Examining Zero-Shot Vulnerability Repair with Large Language Models
2023 IEEE Symposium on Security and Privacy (SP)
2021 - 104 citations
-
Show abstract
-
Cite
- PDF
4.0%
topic match
3.9%
0.0
2023
[314] Consistency of Code: A Prompt Based Approach to Comprehend Functionality
2023 30th Asia-Pacific Software Engineering Conference (APSEC)
2023 - 0 citations
-
Show abstract
-
Cite
3.9%
topic match
3.9%
4.2
2023
[315] Testing LLMs on Code Generation with Varying Levels of Prompt Specificity
ArXiv
2023 - 4 citations
-
Show abstract
-
Cite
- PDF
3.9%
topic match
3.9%
1.5
2023
[316] Copilot for Xcode: Exploring AI-Assisted Programming by Prompting Cloud-based Large Language Models
ArXiv
2023 - 2 citations
-
Show abstract
-
Cite
- PDF
3.9%
topic match
3.9%
0.0
2024
3.9%
31.9
2023
[318] MetaAgents: Simulating Interactions of Human Behaviors for LLM-based Task-oriented Coordination via Collaborative Generative Agents
ArXiv
2023 - 33 citations
-
Show abstract
-
Cite
- PDF
3.9%
topic match
3.8%
0.0
2024
[319] From Trends to Experiences: Co-Creation with Generative Artificial Intelligence in Developing Interactive Multimedia Applications
CLEI Electron. J.
2024 - 0 citations
-
Show abstract
-
Cite
3.8%
topic match
3.8%
4.2
2024
[320] Ocassionally Secure: A Comparative Analysis of Code Generation Assistants
ArXiv
2024 - 3 citations
-
Show abstract
-
Cite
- PDF
3.8%
topic match
3.8%
3.0
2022
[321] Aligning Offline Metrics and Human Judgments of Value for Code Generation Models
Annual Meeting of the Association for Computational Linguistics
2022 - 6 citations
-
Show abstract
-
Cite
- PDF
3.8%
topic match
3.8%
0
None
[322] MoonBit: Explore the Design of an AI-Friendly Programming Language
Journal Not Provided
None - 0 citations
-
Show abstract
-
Cite
3.8%
topic match
3.8%
0
None
[323] Beyond Code Generation: Unveiling Chatgpt's Potential For The Software Development Workflow
Journal Not Provided
None - 0 citations
-
Show abstract
-
Cite
3.8%
topic match
3.8%
0.0
2024
[324] Improving Natural Language Capability of Code Large Language Model
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
3.8%
topic match
3.7%
6.4
2024
[325] DebugBench: Evaluating Debugging Capability of Large Language Models
ArXiv
2024 - 5 citations
-
Show abstract
-
Cite
- PDF
3.7%
topic match
3.7%
0.0
2024
[326] S3LLM: Large-Scale Scientific Software Understanding with LLMs using Source, Metadata, and Document
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
3.7%
topic match
3.7%
0.0
2024
3.7%
296.0
2022
[328] Competition-level code generation with AlphaCode
Science
2022 - 800 citations
-
Show abstract
-
Cite
- PDF
3.7%
topic match
3.7%
0.0
2023
[329] Human-AI Collaboration in Thematic Analysis using ChatGPT: A User Study and Design Recommendations
ArXiv
2023 - 0 citations
-
Show abstract
-
Cite
- PDF
3.7%
topic match
3.6%
0
None
[330] Tackling Students’ Coding Assignments with LLMs
Journal Not Provided
None - 0 citations
-
Show abstract
-
Cite
3.6%
topic match
3.6%
4.2
2023
3.6%
None
None
[332] ChatGPT in Action: Analyzing Its Use in Software Development
Journal Not Provided
None - 2 citations
-
Show abstract
-
Cite
3.6%
topic match
3.6%
4.0
2024
[333] A Survey on Self-Evolution of Large Language Models
ArXiv
2024 - 2 citations
-
Show abstract
-
Cite
- PDF
3.6%
topic match
3.6%
8.3
2023
[334] No Need to Lift a Finger Anymore? Assessing the Quality of Code Generation by ChatGPT
ArXiv
2023 - 10 citations
-
Show abstract
-
Cite
- PDF
3.6%
topic match
3.6%
1.1
2023
[335] LLM4TDD: Best Practices for Test Driven Development Using Large Language Models
ArXiv
2023 - 1 citations
-
Show abstract
-
Cite
- PDF
3.6%
topic match
3.6%
2.1
2023
[336] Assessing the Promise and Pitfalls of ChatGPT for Automated Code Generation
ArXiv
2023 - 2 citations
-
Show abstract
-
Cite
- PDF
3.6%
topic match
3.5%
1.6
2023
3.5%
1.3
2024
[338] Interactions with Prompt Problems: A New Way to Teach Programming with Large Language Models
ArXiv
2024 - 1 citations
-
Show abstract
-
Cite
- PDF
3.5%
topic match
3.5%
5.7
2023
[339] ChatGPT for PLC/DCS Control Logic Generation
2023 IEEE 28th International Conference on Emerging Technologies and Factory Automation (ETFA)
2023 - 8 citations
-
Show abstract
-
Cite
- PDF
3.5%
topic match
3.5%
1.0
2020
[340] Machine Learning-Based Code Auto-Completion Implementation for Firmware Developers
Applied Sciences
2020 - 4 citations
-
Show abstract
-
Cite
3.5%
topic match
3.5%
14.4
2023
[341] Understanding the Usability of AI Programming Assistants
ArXiv
2023 - 26 citations
-
Show abstract
-
Cite
3.5%
topic match
3.5%
0.0
2024
[342] Prompt-based Code Completion via Multi-Retrieval Augmented Generation
Journal Not Provided
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
3.5%
topic match
3.5%
1.4
2024
[343] Assured LLM-Based Software Engineering
ArXiv
2024 - 1 citations
-
Show abstract
-
Cite
- PDF
3.5%
topic match
3.5%
14.7
2023
[344] Prompt Problems: A New Programming Exercise for the Generative AI Era
ArXiv
2023 - 14 citations
-
Show abstract
-
Cite
- PDF
3.5%
topic match
3.4%
0.0
2024
[345] CodeBenchGen: Creating Scalable Execution-based Code Generation Benchmarks
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
3.4%
topic match
3.4%
7.2
2023
[346] A Survey on Large Language Models for Software Engineering
ArXiv
2023 - 6 citations
-
Show abstract
-
Cite
- PDF
3.4%
topic match
3.4%
0.0
2023
[347] AskIt: Unified Programming Interface for Programming with Large Language Models
2024 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)
2023 - 0 citations
-
Show abstract
-
Cite
- PDF
3.4%
topic match
3.4%
0.0
2024
[348] MHPP: Exploring the Capabilities and Limitations of Language Models Beyond Basic Code Generation
Journal Not Provided
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
3.4%
topic match
3.4%
9.8
2022
[349] Execution-based Evaluation for Data Science Code Generation Models
ArXiv
2022 - 19 citations
-
Show abstract
-
Cite
- PDF
3.4%
topic match
3.4%
0.0
2023
[350] Regulating the use of generative AI in academic research and publications
PUBMET
2023 - 0 citations
-
Show abstract
-
Cite
3.4%
topic match
3.3%
0.0
2024
[351] Smurfs: Leveraging Multiple Proficiency Agents with Context-Efficiency for Tool Planning
Journal Not Provided
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
3.3%
topic match
3.3%
0.0
2024
[352] Knowledge-Aware Code Generation with Large Language Models
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
3.3%
topic match
3.3%
3.1
2023
[353] Exploring the Problems, their Causes and Solutions of AI Pair Programming: A Study with Practitioners of GitHub Copilot
Journal Not Provided
2023 - 3 citations
-
Show abstract
-
Cite
- PDF
3.3%
topic match
3.3%
4.5
2023
[354] On the Effectiveness of Large Language Models in Domain-Specific Code Generation
ArXiv
2023 - 4 citations
-
Show abstract
-
Cite
- PDF
3.3%
topic match
3.3%
3.7
2024
[355] On Evaluating the Efficiency of Source Code Generated by LLMs
ArXiv
2024 - 2 citations
-
Show abstract
-
Cite
- PDF
3.3%
topic match
3.3%
5.7
2023
3.2%
8.8
2022
3.2%
0.0
2023
[358] CERN for AGI: A Theoretical Framework for Autonomous Simulation-Based Artificial Intelligence Testing and Alignment
ArXiv
2023 - 0 citations
-
Show abstract
-
Cite
- PDF
3.2%
topic match
3.2%
191.5
2023
[359] WizardCoder: Empowering Code Large Language Models with Evol-Instruct
ArXiv
2023 - 260 citations
-
Show abstract
-
Cite
- PDF
3.2%
topic match
3.2%
9.5
2022
[360] Piloting Copilot and Codex: Hot Temperature, Cold Prompts, or Black Magic?
ArXiv
2022 - 19 citations
-
Show abstract
-
Cite
- PDF
3.2%
topic match
3.2%
2.4
2023
[361] A Prompt Learning Framework for Source Code Summarization
ArXiv
2023 - 2 citations
-
Show abstract
-
Cite
- PDF
3.2%
topic match
3.2%
0.0
2024
3.2%
3.1
2023
[363] Can ChatGPT advance software testing intelligence? An experience report on metamorphic testing
ArXiv
2023 - 3 citations
-
Show abstract
-
Cite
- PDF
3.2%
topic match
3.2%
0.0
2023
[364] On Automated Assistants for Software Development: The Role of LLMs
2023 38th IEEE/ACM International Conference on Automated Software Engineering (ASE)
2023 - 0 citations
-
Show abstract
-
Cite
3.2%
topic match
3.2%
0.0
2024
[365] Neural Models for Source Code Synthesis and Completion
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
3.2%
topic match
3.2%
10.5
2021
[366] An Empirical Cybersecurity Evaluation of GitHub Copilot's Code Contributions
ArXiv
2021 - 40 citations
-
Show abstract
-
Cite
3.2%
topic match
3.2%
0
None
3.1%
1.7
2023
[368] Study of software developers' experience using the Github Copilot Tool in the software development process
ArXiv
2023 - 3 citations
-
Show abstract
-
Cite
- PDF
3.1%
topic match
3.1%
0.0
2023
[369] Building Trust in AI -A Simplified Guide to Ensure Software Quality
Journal of Soft Computing Paradigm
2023 - 0 citations
-
Show abstract
-
Cite
3.1%
topic match
3.1%
2.1
2023
[370] Evaluating In-Context Learning of Libraries for Code Generation
ArXiv
2023 - 2 citations
-
Show abstract
-
Cite
- PDF
3.1%
topic match
3.1%
0.0
2023
3.1%
4.4
2021
[372] CGEMs: A Metric Model for Automatic Code Generation using GPT-3
ArXiv
2021 - 14 citations
-
Show abstract
-
Cite
- PDF
3.1%
topic match
3.1%
14.5
2023
[373] Towards an Understanding of Large Language Models in Software Engineering Tasks
ArXiv
2023 - 17 citations
-
Show abstract
-
Cite
- PDF
3.1%
topic match
3.0%
6.1
2023
[374] The (ab)use of Open Source Code to Train Large Language Models
2023 IEEE/ACM 2nd International Workshop on Natural Language-Based Software Engineering (NLBSE)
2023 - 10 citations
-
Show abstract
-
Cite
- PDF
3.0%
topic match
3.0%
0.1
2007
[375] Toward automated software development
Proceedings of the 22nd IEEE/ACM International Conference on Automated Software Engineering
2007 - 2 citations
-
Show abstract
-
Cite
3.0%
topic match
3.0%
0.0
2023
[376] Seq2Seq or Seq2Tree: Generating Code Using Both Paradigms via Mutual Learning
Proceedings of the 14th Asia-Pacific Symposium on Internetware
2023 - 0 citations
-
Show abstract
-
Cite
3.0%
topic match
3.0%
1.7
2023
[377] GrACE: Generation using Associated Code Edits
ArXiv
2023 - 3 citations
-
Show abstract
-
Cite
3.0%
topic match
3.0%
228.1
2022
[378] Large Language Models Are Human-Level Prompt Engineers
ArXiv
2022 - 449 citations
-
Show abstract
-
Cite
- PDF
3.0%
topic match
3.0%
1.5
2024
[379] AI-Assisted Programming Tasks Using Code Embeddings and Transformers
Electronics
2024 - 1 citations
-
Show abstract
-
Cite
3.0%
topic match
3.0%
10.7
2023
[380] Large Language Models and Simple, Stupid Bugs
2023 IEEE/ACM 20th International Conference on Mining Software Repositories (MSR)
2023 - 17 citations
-
Show abstract
-
Cite
- PDF
3.0%
topic match
2.9%
13.0
2022
[381] Fault-Aware Neural Code Rankers
ArXiv
2022 - 31 citations
-
Show abstract
-
Cite
- PDF
2.9%
topic match
2.9%
0.0
2024
[382] CMAT: A Multi-Agent Collaboration Tuning Framework for Enhancing Small Language Models
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
2.9%
topic match
2.9%
0.0
2024
[383] Guiding Enumerative Program Synthesis with Large Language Models
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
2.9%
topic match
2.9%
38.7
2022
[384] Synchromesh: Reliable code generation from pre-trained language models
ArXiv
2022 - 106 citations
-
Show abstract
-
Cite
- PDF
2.9%
topic match
2.9%
13.0
2023
[385] Towards Generating Functionally Correct Code Edits from Natural Language Issue Descriptions
ArXiv
2023 - 20 citations
-
Show abstract
-
Cite
- PDF
2.9%
topic match
2.9%
1.7
2024
[386] Evaluating Large Language Models with Runtime Behavior of Program Execution
ArXiv
2024 - 1 citations
-
Show abstract
-
Cite
- PDF
2.9%
topic match
2.9%
0.0
2024
[387] AgentCoord: Visually Exploring Coordination Strategy for LLM-based Multi-Agent Collaboration
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
2.9%
topic match
2.9%
8.7
2023
[388] Controlling Large Language Model-based Agents for Large-Scale Decision-Making: An Actor-Critic Approach
ArXiv
2023 - 8 citations
-
Show abstract
-
Cite
- PDF
2.9%
topic match
2.9%
2.2
2023
[389] The Transformative Influence of Large Language Models on Software Development
ArXiv
2023 - 2 citations
-
Show abstract
-
Cite
- PDF
2.9%
topic match
2.9%
33.2
2023
[390] Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View
ArXiv
2023 - 35 citations
-
Show abstract
-
Cite
- PDF
2.9%
topic match
2.8%
48.0
2023
[391] MultiPL-E: A Scalable and Polyglot Approach to Benchmarking Neural Code Generation
IEEE Transactions on Software Engineering
2023 - 63 citations
-
Show abstract
-
Cite
2.8%
topic match
2.8%
0.0
2024
2.8%
0.0
2024
[393] Using artificial intelligence for economic research: An agricultural odyssey
Australian Journal of Agricultural and Resource Economics
2024 - 0 citations
-
Show abstract
-
Cite
2.8%
topic match
2.8%
0.0
2023
[394] A User-centered Security Evaluation of Copilot
International Conference on Software Engineering
2023 - 0 citations
-
Show abstract
-
Cite
- PDF
2.8%
topic match
2.8%
0.0
2023
[395] Human, What Must I Tell You?
IEEE Software
2023 - 0 citations
-
Show abstract
-
Cite
2.8%
topic match
2.8%
6.4
2023
[396] Code Prompting: a Neural Symbolic Method for Complex Reasoning in Large Language Models
ArXiv
2023 - 9 citations
-
Show abstract
-
Cite
- PDF
2.8%
topic match
2.7%
3.0
2023
[397] Exploring Large Language Models for Code Explanation
ArXiv
2023 - 3 citations
-
Show abstract
-
Cite
- PDF
2.7%
topic match
2.7%
2.2
2023
[398] AutoScrum: Automating Project Planning Using Large Language Models
Journal Not Provided
2023 - 3 citations
-
Show abstract
-
Cite
- PDF
2.7%
topic match
2.7%
3.2
2023
[399] Conceptual Model Interpreter for Large Language Models
ArXiv
2023 - 3 citations
-
Show abstract
-
Cite
- PDF
2.7%
topic match
2.7%
0.0
2024
[400] A Survey on Large Language Models from Concept to Implementation
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
2.7%
topic match
2.6%
1.4
2022
2.6%
3.1
2021
2.6%
0.9
2023
[403] Frustrated with Code Quality Issues? LLMs can Help!
ArXiv
2023 - 1 citations
-
Show abstract
-
Cite
- PDF
2.6%
topic match
2.6%
20.0
2021
[404] Few-Shot Semantic Parsing with Language Models Trained on Code
North American Chapter of the Association for Computational Linguistics
2021 - 57 citations
-
Show abstract
-
Cite
- PDF
2.6%
topic match
2.6%
1.2
2023
[405] Enhancing Robot Program Synthesis Through Environmental Context
ArXiv
2023 - 1 citations
-
Show abstract
-
Cite
- PDF
2.6%
topic match
2.5%
8.1
2023
[406] Evaluating ChatGPT and GPT-4 for Visual Programming
Proceedings of the 2023 ACM Conference on International Computing Education Research - Volume 2
2023 - 10 citations
-
Show abstract
-
Cite
- PDF
2.5%
topic match
2.5%
18.2
2022
[407] Interactive Code Generation via Test-Driven User-Intent Formalization
ArXiv
2022 - 40 citations
-
Show abstract
-
Cite
- PDF
2.5%
topic match
2.5%
4.0
2024
[408] PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety
ArXiv
2024 - 3 citations
-
Show abstract
-
Cite
- PDF
2.5%
topic match
2.5%
17.5
2023
[409] A Critical Review of Large Language Model on Software Engineering: An Example from ChatGPT and Automated Program Repair
ArXiv
2023 - 18 citations
-
Show abstract
-
Cite
- PDF
2.5%
topic match
2.5%
78.7
2023
[410] Large Language Models as Tool Makers
ArXiv
2023 - 111 citations
-
Show abstract
-
Cite
- PDF
2.5%
topic match
2.5%
0.0
2024
[411] Quality Assessment of Prompts Used in Code Generation
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
2.5%
topic match
2.5%
0.0
2024
[412] Developing Time Series Forecasting Models with Generative Large Language Models
ACM Transactions on Intelligent Systems and Technology
2024 - 0 citations
-
Show abstract
-
Cite
2.5%
topic match
2.4%
0.0
2024
[413] Can LLM-Augmented autonomous agents cooperate?, An evaluation of their cooperative capabilities through Melting Pot
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
2.4%
topic match
2.4%
0.0
2023
[414] ARTIFICIAL INTELLIGENCE CHATBOTS – A HELP OR HINDRANCE TO COMPUTER SCIENCE EDUCATION
Education and New Developments 2023 – Volume 2
2023 - 0 citations
-
Show abstract
-
Cite
2.4%
topic match
2.4%
1.6
2024
[415] Evaluating the Application of Large Language Models to Generate Feedback in Programming Education
ArXiv
2024 - 1 citations
-
Show abstract
-
Cite
- PDF
2.4%
topic match
2.4%
18.0
2019
[416] Learning to Infer Program Sketches
ArXiv
2019 - 102 citations
-
Show abstract
-
Cite
- PDF
2.4%
topic match
2.4%
0.0
2023
[417] Do Robots Dream of Passing a Programming Course?
2023 42nd IEEE International Conference of the Chilean Computer Science Society (SCCC)
2023 - 0 citations
-
Show abstract
-
Cite
2.4%
topic match
2.4%
1.8
2023
2.3%
0.0
2020
[419] Bidirectional Transformer Language Models for Smart Autocompletion of Source Code
https://doi.org/10.18420/inf2020_83
2020 - 0 citations
-
Show abstract
-
Cite
2.3%
topic match
2.3%
2.2
2023
[420] Improving Knowledge Extraction from LLMs for Robotic Task Learning through Agent Analysis
ArXiv
2023 - 4 citations
-
Show abstract
-
Cite
2.3%
topic match
2.3%
9.7
2023
[421] Benchmarking and Explaining Large Language Model-based Code Generation: A Causality-Centric Approach
ArXiv
2023 - 10 citations
-
Show abstract
-
Cite
- PDF
2.3%
topic match
2.3%
16.0
2022
[422] Automatic Code Documentation Generation Using GPT-3
Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering
2022 - 34 citations
-
Show abstract
-
Cite
- PDF
2.3%
topic match
2.3%
3.5
2023
[423] Hot or Cold? Adaptive Temperature Sampling for Code Generation with Large Language Models
AAAI Conference on Artificial Intelligence
2023 - 4 citations
-
Show abstract
-
Cite
- PDF
2.3%
topic match
2.3%
1.3
2024
2.3%
45.3
2022
[425] Multi-lingual Evaluation of Code Generation Models
ArXiv
2022 - 90 citations
-
Show abstract
-
Cite
- PDF
2.3%
topic match
2.2%
22.4
2023
[426] AutoML-GPT: Automatic Machine Learning with GPT
ArXiv
2023 - 33 citations
-
Show abstract
-
Cite
- PDF
2.2%
topic match
2.2%
39.6
2022
[427] Large Language Models Meet NL2Code: A Survey
Annual Meeting of the Association for Computational Linguistics
2022 - 73 citations
-
Show abstract
-
Cite
- PDF
2.2%
topic match
2.2%
22.3
2023
[428] Retrieval-Based Prompt Selection for Code-Related Few-Shot Learning
2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE)
2023 - 33 citations
-
Show abstract
-
Cite
2.2%
topic match
2.2%
8.9
2023
[429] Towards Enhancing In-Context Learning for Code Generation
ArXiv
2023 - 16 citations
-
Show abstract
-
Cite
2.2%
topic match
2.2%
24.3
2023
[430] SkCoder: A Sketch-based Approach for Automatic Code Generation
2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE)
2023 - 41 citations
-
Show abstract
-
Cite
- PDF
2.2%
topic match
2.1%
0.5
2016
2.1%
3.9
2017
[432] Program synthesis: challenges and opportunities
Philosophical transactions. Series A, Mathematical, physical, and engineering sciences
2017 - 28 citations
-
Show abstract
-
Cite
2.1%
topic match
2.1%
4.3
2023
[433] MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration
ArXiv
2023 - 4 citations
-
Show abstract
-
Cite
- PDF
2.1%
topic match
2.1%
1.8
2023
[434] PwR: Exploring the Role of Representations in Conversational Programming
ArXiv
2023 - 2 citations
-
Show abstract
-
Cite
- PDF
2.1%
topic match
2.1%
0.0
2017
[435] Deep Learning for Compilers First Year Review Document
Journal Not Provided
2017 - 0 citations
-
Show abstract
-
Cite
2.1%
topic match
2.0%
0.0
2024
[436] Program Decomposition and Translation with Static Analysis
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
2.0%
topic match
2.0%
0.0
2024
[437] Toward Automated Programming for Robotic Assembly Using ChatGPT
Journal Not Provided
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
2.0%
topic match
2.0%
1.4
2024
[438] Exploring Interaction Patterns for Debugging: Enhancing Conversational Capabilities of AI-assistants
ArXiv
2024 - 1 citations
-
Show abstract
-
Cite
- PDF
2.0%
topic match
2.0%
3.6
2023
[439] Analysis of the Application of Generative AI in Business Management
Advances in Economics and Management Research
2023 - 5 citations
-
Show abstract
-
Cite
2.0%
topic match
2.0%
0.0
2024
2.0%
1.8
2017
[441] AP: Artificial Programming
Summit on Advances in Programming Languages
2017 - 13 citations
-
Show abstract
-
Cite
2.0%
topic match
1.9%
0.0
2024
[442] Analysis of Computer Application Software Automation Development Technology
Advances in Computer and Communication
2024 - 0 citations
-
Show abstract
-
Cite
1.9%
topic match
1.9%
0.0
2023
[443] Tech Report Generative AI
https://doi.org/10.18235/0005105
2023 - 0 citations
-
Show abstract
-
Cite
1.9%
topic match
1.9%
6.1
2023
[444] ModelScope-Agent: Building Your Customizable Agent System with Open-source Large Language Models
ArXiv
2023 - 7 citations
-
Show abstract
-
Cite
- PDF
1.9%
topic match
1.9%
26.1
2019
[445] Write, Execute, Assess: Program Synthesis with a REPL
Neural Information Processing Systems
2019 - 140 citations
-
Show abstract
-
Cite
- PDF
1.9%
topic match
1.9%
3.3
2024
[446] Software Vulnerability and Functionality Assessment using LLMs
ArXiv
2024 - 2 citations
-
Show abstract
-
Cite
- PDF
1.9%
topic match
1.8%
0.0
2023
[447] Assessment of ChatGPT's Proficiency in Software Development
2023 Congress in Computer Science, Computer Engineering, & Applied Computing (CSCE)
2023 - 0 citations
-
Show abstract
-
Cite
1.8%
topic match
1.8%
15.5
2023
[448] Making Language Models Better Tool Learners with Execution Feedback
ArXiv
2023 - 22 citations
-
Show abstract
-
Cite
- PDF
1.8%
topic match
1.8%
0.0
2023
1.8%
306.5
2023
[450] The Rise and Potential of Large Language Model Based Agents: A Survey
ArXiv
2023 - 339 citations
-
Show abstract
-
Cite
- PDF
1.8%
topic match
1.8%
31.8
2023
[451] How Secure is Code Generated by ChatGPT?
2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)
2023 - 48 citations
-
Show abstract
-
Cite
- PDF
1.8%
topic match
1.8%
4.6
2022
[452] When Neural Model Meets NL2Code: A Survey
ArXiv
2022 - 13 citations
-
Show abstract
-
Cite
1.8%
topic match
1.8%
2.6
2023
1.8%
0.0
2024
[454] Development in times of hype: How freelancers explore Generative AI?
International Conference on Software Engineering
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
1.8%
topic match
1.8%
2.8
2023
[455] COLDECO: An End User Spreadsheet Inspection Tool for AI-Generated Code
2023 IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC)
2023 - 3 citations
-
Show abstract
-
Cite
1.8%
topic match
1.8%
0.5
2013
1.7%
0.0
2024
[457] SpreadNaLa: A Naturalistic Code Generation Evaluation Dataset of Spreadsheet Formulas
International Conference on Language Resources and Evaluation
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
1.7%
topic match
1.7%
14.7
2023
1.7%
1.4
2024
[459] Governance of Generative Artificial Intelligence for Companies
ArXiv
2024 - 1 citations
-
Show abstract
-
Cite
- PDF
1.7%
topic match
1.7%
36.6
2018
[460] Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow
2018 IEEE/ACM 15th International Conference on Mining Software Repositories (MSR)
2018 - 235 citations
-
Show abstract
-
Cite
- PDF
1.7%
topic match
1.7%
5.6
2024
[461] Professional Agents - Evolving Large Language Models into Autonomous Experts with Human-Level Competencies
ArXiv
2024 - 4 citations
-
Show abstract
-
Cite
- PDF
1.7%
topic match
1.7%
0.0
2023
1.7%
0.5
2022
1.7%
0.0
2021
[464] Deep Learning Based Code Generation from Requirements Text: Are We There Yet?
Journal Not Provided
2021 - 0 citations
-
Show abstract
-
Cite
1.7%
topic match
1.7%
63.2
2023
[465] Large Language Models for Software Engineering: A Systematic Literature Review
ArXiv
2023 - 74 citations
-
Show abstract
-
Cite
- PDF
1.7%
topic match
1.6%
4.2
2024
[466] Can Large Language Models Serve as Data Analysts? A Multi-Agent Assisted Approach for Qualitative Data Analysis
ArXiv
2024 - 3 citations
-
Show abstract
-
Cite
- PDF
1.6%
topic match
1.6%
0.7
2022
[467] C3PO: A Lightweight Copying Mechanism for Translating Pseudocode to Code
Journal Not Provided
2022 - 2 citations
-
Show abstract
-
Cite
- PDF
1.6%
topic match
1.5%
30.7
2023
[468] VerilogEval: Evaluating Large Language Models for Verilog Code Generation
ArXiv
2023 - 34 citations
-
Show abstract
-
Cite
- PDF
1.5%
topic match
1.5%
10.3
2023
[469] CGMI: Configurable General Multi-Agent Interaction Framework
ArXiv
2023 - 12 citations
-
Show abstract
-
Cite
- PDF
1.5%
topic match
1.5%
1.3
2024
[470] Exploring the Potential of Large Language Models in Self-adaptive Systems
https://doi.org/10.48550/arXiv.2401.07534
2024 - 1 citations
-
Show abstract
-
Cite
- PDF
1.5%
topic match
1.5%
1.1
2023
[471] Exploring the Limits of ChatGPT in Software Security Applications
ArXiv
2023 - 1 citations
-
Show abstract
-
Cite
- PDF
1.5%
topic match
1.5%
0.0
2024
[472] PromptSet: A Programmer's Prompting Dataset
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
1.5%
topic match
1.4%
0.0
1999
1.4%
41.7
2023
[474] How Generative AI models such as ChatGPT can be (Mis)Used in SPC Practice, Education, and Research? An Exploratory Study
ArXiv
2023 - 70 citations
-
Show abstract
-
Cite
- PDF
1.4%
topic match
1.4%
144.4
2022
[475] A systematic evaluation of large language models of code
Proceedings of the 6th ACM SIGPLAN International Symposium on Machine Programming
2022 - 383 citations
-
Show abstract
-
Cite
- PDF
1.4%
topic match
1.4%
3.2
2023
[476] CompCodeVet: A Compiler-guided Validation and Enhancement Approach for Code Dataset
ArXiv
2023 - 3 citations
-
Show abstract
-
Cite
- PDF
1.4%
topic match
1.3%
4.1
2022
1.3%
25.8
2023
[478] How ChatGPT Will Change Software Engineering Education
Proceedings of the 2023 Conference on Innovation and Technology in Computer Science Education V. 1
2023 - 34 citations
-
Show abstract
-
Cite
1.3%
topic match
1.3%
12.7
2023
[479] ALGO: Synthesizing Algorithmic Programs with Generated Oracle Verifiers
ArXiv
2023 - 18 citations
-
Show abstract
-
Cite
- PDF
1.3%
topic match
1.3%
0.0
2023
[480] Novel Preprocessing Technique for Data Embedding in Engineering Code Generation Using Large Language Model
Journal Not Provided
2023 - 0 citations
-
Show abstract
-
Cite
- PDF
1.3%
topic match
1.3%
0.0
2024
[481] Exploring the use of ChatGPT in learning and instructing statistics and data analytics
Teaching Statistics
2024 - 0 citations
-
Show abstract
-
Cite
1.3%
topic match
1.3%
0.0
2024
[482] Unveiling Disparities in Web Task Handling Between Human and Web Agent
Journal Not Provided
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
1.3%
topic match
1.3%
12.6
2023
[483] Comparing Software Developers with ChatGPT: An Empirical Investigation
ArXiv
2023 - 18 citations
-
Show abstract
-
Cite
- PDF
1.3%
topic match
1.3%
0.0
2024
[484] Adopting Generative AI for Literature Reviews: An Epistemological Perspective
Hawaii International Conference on System Sciences
2024 - 0 citations
-
Show abstract
-
Cite
1.3%
topic match
1.3%
0.0
2023
[485] MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
Journal Not Provided
2023 - 0 citations
-
Show abstract
-
Cite
1.3%
topic match
1.2%
0.7
2023
[486] Code Generation for Collectible Card Games with Complex APIs
The International FLAIRS Conference Proceedings
2023 - 1 citations
-
Show abstract
-
Cite
1.2%
topic match
1.2%
1.1
2023
1.2%
0.0
2024
[488] Legal Aspects for Software Developers Interested in Generative AI Applications
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
1.2%
topic match
1.2%
1.4
2023
[489] The Good, the Bad, and the Missing: Neural Code Generation for Machine Learning Tasks
ACM Transactions on Software Engineering and Methodology
2023 - 2 citations
-
Show abstract
-
Cite
- PDF
1.2%
topic match
1.2%
7.8
2023
[490] GameGPT: Multi-agent Collaborative Framework for Game Development
ArXiv
2023 - 8 citations
-
Show abstract
-
Cite
- PDF
1.2%
topic match
1.2%
7.6
2023
[491] Balancing Autonomy and Alignment: A Multi-Dimensional Taxonomy for Autonomous LLM-powered Multi-Agent Architectures
ArXiv
2023 - 8 citations
-
Show abstract
-
Cite
- PDF
1.2%
topic match
1.2%
1.8
2024
[492] Enhancing the General Agent Capabilities of Low-Parameter LLMs through Tuning and Multi-Branch Reasoning
ArXiv
2024 - 1 citations
-
Show abstract
-
Cite
- PDF
1.2%
topic match
1.1%
0.5
2019
[493] Artificial intelligence for software development — the present and the challenges for the future
Bulletin of the Military University of Technology
2019 - 3 citations
-
Show abstract
-
Cite
1.1%
topic match
1.1%
2.0
2023
1.1%
0.0
2024
[495] Large Language Model-Enabled Multi-Agent Manufacturing Systems
Journal Not Provided
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
1.1%
topic match
1.0%
1.2
2023
[496] An Infinity of Pong: A Raspberry Pi Pico W handheld writes its own games
IEEE Spectrum
2023 - 2 citations
-
Show abstract
-
Cite
1.0%
topic match
0.9%
0
None
[497] Is Attention All You Need? Toward a Conceptual Model for Social Awareness in Large Language Models
Journal Not Provided
None - 0 citations
-
Show abstract
-
Cite
0.9%
topic match
0.9%
2.0
2019
0.9%
5.0
2024
[499] Embodied LLM Agents Learn to Cooperate in Organized Teams
ArXiv
2024 - 3 citations
-
Show abstract
-
Cite
- PDF
0.9%
topic match
0.9%
0.2
2020
0.9%
34.8
2023
[501] “It’s Weird That it Knows What I Want”: Usability and Interactions with Copilot for Novice Programmers
ACM Transactions on Computer-Human Interaction
2023 - 54 citations
-
Show abstract
-
Cite
- PDF
0.9%
topic match
0.9%
0.0
2023
0.9%
0.0
2023
0.9%
11.3
2022
[504] Automatically Generating CS Learning Materials with Large Language Models
Proceedings of the 54th ACM Technical Symposium on Computer Science Education V. 2
2022 - 30 citations
-
Show abstract
-
Cite
- PDF
0.9%
topic match
0.8%
5.3
2024
[505] Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM
ArXiv
2024 - 3 citations
-
Show abstract
-
Cite
- PDF
0.8%
topic match
0.8%
1.9
2023
[506] How to Teach Programming in the AI Era? Using LLMs as a Teachable Agent for Debugging
Journal Not Provided
2023 - 2 citations
-
Show abstract
-
Cite
- PDF
0.8%
topic match
0.7%
11.0
2023
[507] Cooperation on the Fly: Exploring Language Agents for Ad Hoc Teamwork in the Avalon Game
ArXiv
2023 - 9 citations
-
Show abstract
-
Cite
- PDF
0.7%
topic match
0.7%
2.9
2024
[508] A Trembling House of Cards? Mapping Adversarial Attacks against Language Agents
ArXiv
2024 - 2 citations
-
Show abstract
-
Cite
- PDF
0.7%
topic match
0.6%
0.0
2023
[509] The AI-powered PM Toolkit - A Project Manager’s Guide to Thrive the Generative AI Wave
Journal of Artificial Intelligence & Cloud Computing
2023 - 0 citations
-
Show abstract
-
Cite
0.6%
topic match
0.6%
0.0
2024
[510] Analysis and Advancement in Domain-Specific Templated Question Answering
Software Engineering & Trends
2024 - 0 citations
-
Show abstract
-
Cite
0.6%
topic match
0.6%
8.7
2023
[511] ICE-Score: Instructing Large Language Models to Evaluate Code
Findings
2023 - 13 citations
-
Show abstract
-
Cite
- PDF
0.6%
topic match
0.6%
6.7
2023
[512] Generative Artificial Intelligence in Learning Analytics: Contextualising Opportunities and Challenges through the Learning Analytics Cycle
ArXiv
2023 - 6 citations
-
Show abstract
-
Cite
- PDF
0.6%
topic match
0.6%
8.0
2023
[513] Fully Autonomous Programming with Large Language Models
Proceedings of the Genetic and Evolutionary Computation Conference
2023 - 12 citations
-
Show abstract
-
Cite
- PDF
0.6%
topic match
0.6%
0.0
2023
[514] A Review of Repository Level Prompting for LLMs
ArXiv
2023 - 0 citations
-
Show abstract
-
Cite
- PDF
0.6%
topic match
0.6%
1.4
2023
[515] Evaluating GPT's Programming Capability through CodeWars' Katas
ArXiv
2023 - 2 citations
-
Show abstract
-
Cite
- PDF
0.6%
topic match
0.6%
0.0
2024
[516] Using ChatGPT in Software Requirements Engineering: A Comprehensive Review
Future Internet
2024 - 0 citations
-
Show abstract
-
Cite
0.6%
topic match
0.5%
2.3
2023
0.5%
1.8
2024
[518] CoderUJB: An Executable and Unified Java Benchmark for Practical Programming Scenarios
ArXiv
2024 - 1 citations
-
Show abstract
-
Cite
- PDF
0.5%
topic match
0.5%
0.4
2015
[519] Program synthesis: opportunities for the next decade
Proceedings of the 20th ACM SIGPLAN International Conference on Functional Programming
2015 - 4 citations
-
Show abstract
-
Cite
0.5%
topic match
0.5%
1.3
2024
0.5%
0.0
2024
0.4%
0.0
2024
[522] A Preliminary Study on Using Large Language Models in Software Pentesting
ArXiv
2024 - 0 citations
-
Show abstract
-
Cite
- PDF
0.4%
topic match
0.4%
5.2
2018
[523] Investigating the Prospects of Generative Artificial Intelligence
Asian Journal of Humanity, Art and Literature
2018 - 30 citations
-
Show abstract
-
Cite
0.4%
topic match
0.4%
None
None
[524] Program synthesis for integer sequence generation
Journal Not Provided
None - 1 citations
-
Show abstract
-
Cite
0.4%
topic match
0.4%
4.1
2023
0.3%
2.7
2024
[526] How Beginning Programmers and Code LLMs (Mis)read Each Other
International Conference on Human Factors in Computing Systems
2024 - 2 citations
-
Show abstract
-
Cite
- PDF
0.3%
topic match
0.3%
1.9
2023
[527] LLM4VV: Developing LLM-Driven Testsuite for Compiler Validation
ArXiv
2023 - 2 citations
-
Show abstract
-
Cite
- PDF
0.3%
topic match
0.3%
5.1
2018
[528] Recent Advances in Neural Program Synthesis
ArXiv
2018 - 34 citations
-
Show abstract
-
Cite
- PDF
0.3%
topic match
0.3%
97.2
2021
[529] Measuring Coding Challenge Competence With APPS
ArXiv
2021 - 333 citations
-
Show abstract
-
Cite
- PDF
0.3%
topic match
0.3%
24.4
2022
[530] Lost at C: A User Study on the Security Implications of Large Language Model Code Assistants
USENIX Security Symposium
2022 - 53 citations
-
Show abstract
-
Cite
- PDF
0.3%
topic match
0.2%
18.3
2023
[531] Accelerating Innovation With Generative AI: AI-Augmented Digital Prototyping and Innovation Methods
IEEE Engineering Management Review
2023 - 33 citations
-
Show abstract
-
Cite
0.2%
topic match
0.2%
5.8
2024
[532] Exploring the Potential of Generative Artificial Intelligence
INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT
2024 - 3 citations
-
Show abstract
-
Cite
0.2%
topic match
0.2%
33.2
2023
[533] Thrilled by Your Progress! Large Language Models (GPT-4) No Longer Struggle to Pass Assessments in Higher Education Programming Courses
Proceedings of the 2023 ACM Conference on International Computing Education Research - Volume 1
2023 - 45 citations
-
Show abstract
-
Cite
- PDF
0.2%
topic match
0.2%
0.0
2023
0.2%
3.8
2017
[535] AI programmer: autonomously creating software programs using genetic algorithms
Proceedings of the Genetic and Evolutionary Computation Conference Companion
2017 - 27 citations
-
Show abstract
-
Cite
- PDF
0.2%
topic match
0.1%
0.0
2024
0.1%
6.7
2023
0.1%
43.1
2021
[538] CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks
Journal Not Provided
2021 - 147 citations
-
Show abstract
-
Cite
- PDF
0.1%
topic match
0.1%
1.2
2023
[539] Application of Generative AI for Business Analyst Role
Journal of Artificial Intelligence & Cloud Computing
2023 - 1 citations
-
Show abstract
-
Cite
0.1%
topic match
0.0%
63.7
2021
[540] Asleep at the Keyboard? Assessing the Security of GitHub Copilot’s Code Contributions
2022 IEEE Symposium on Security and Privacy (SP)
2021 - 202 citations
-
Show abstract
-
Cite
- PDF
0.0%
topic match