mlsanityData to 7 Oct 2026

Self-collaboration Code Generation via ChatGPT

arXiv 2304.07590 ↗First posted 15 Apr 2023cs.SEcited by 255

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

Although Large Language Models (LLMs) have demonstrated remarkable code-generation ability, they still struggle with complex tasks. In real-world software development, humans usually tackle complex tasks through collaborative teamwork, a strategy that significantly controls development complexity and enhances software quality. Inspired by this, we present a self-collaboration framework for code generation employing LLMs, exemplified by ChatGPT. Specifically, through role instructions, 1) Multiple LLM agents act as distinct `experts', each responsible for a specific subtask within a complex task; 2) Specify the way to collaborate and interact, so that different roles form a virtual team to facilitate each other's work, ultimately the virtual team addresses code generation tasks collaboratively without the need for human intervention. To effectively organize and manage this virtual team, we incorporate software-development methodology into the framework. Thus, we assemble an elementary team consisting of three LLM roles (i.e., analyst, coder, and tester) responsible for software development's analysis, coding, and testing stages. We conduct comprehensive experiments on various code-generation benchmarks. Experimental results indicate that self-collaboration code generation relatively improves 29.9%-47.1% Pass@1 compared to the base LLM agent. Moreover, we showcase that self-collaboration could potentially enable LLMs to efficiently handle complex repository-level tasks that are not readily solved by the single LLM agent.

Key facts. Cited by 255 papers in the map (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. First posted on arXiv 15 Apr 2023.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 33; 2024: 78; 2025: 94; 2026: 50.

255 papers.

Sort:

By area:

  1. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  2. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  3. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 752
  4. 2023Cognitive Architectures for Language Agentscited by 422
  5. 2023Large Language Models for Software Engineering: A Systematic Literature Reviewcited by 389
  6. 2023A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaborationcited by 281
  7. 2024Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalizationcited by 203
  8. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
  9. 2023OctoPack: Instruction Tuning Code Large Language Modelscited by 178
  10. 2024MapCoder: Multi-Agent Code Generation for Competitive Problem Solvingcited by 177
  11. 2024Large Language Model-Based Agents for Software Engineering: A Surveycited by 173
  12. 2024LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Aheadcited by 155
38 more
  1. 2023User Behavior Simulation with Large Language Model based Agentscited by 136
  2. 2023Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Surveycited by 134
  3. 2024Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospectscited by 130
  4. 2024On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agentscited by 92
  5. 2024From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Futurecited by 85
  6. 2024Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimizationcited by 84
  7. 2024If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agentscited by 77
  8. 2024From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agentscited by 76
  9. 2024Self-Contrast: Better Reflection Through Inconsistent Solving Perspectivescited by 71
  10. 2024EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositoriescited by 71
  11. 2024DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositoriescited by 71
  12. 2023LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplaycited by 62
  13. 2023Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Codecited by 62
  14. 2024Exploring and Unleashing the Power of Large Language Models in Automated Code Translationcited by 57
  15. 2025On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHubcited by 53
  16. 2023Multi-Agent Consensus Seeking via Large Language Modelscited by 50
  17. 2024Autonomous LLM-driven research from data to human-verifiable research paperscited by 50
  18. 2024(Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Textscited by 49
  19. 2025Do as We Do, Not as You Think: the Conformity of Large Language Modelscited by 48
  20. 2025Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMscited by 47
  21. 2023SMILE: Single-turn to Multi-turn Inclusive Language Expansion via ChatGPT for Mental Health Supportcited by 46
  22. 2023Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistencycited by 46
  23. 2024From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debuggingcited by 46
  24. 2023Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedycited by 45
  25. 2023Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Modelscited by 40
  26. 2025Repo2Run: Automated Building Executable Environment for Code Repository at Scalecited by 39
  27. 2024Learning to Ask: When LLM Agents Meet Unclear Instructioncited by 38
  28. 2024Gender Bias in Large Language Models across Multiple Languagescited by 35
  29. 2024UniDebugger: Hierarchical Multi-Agent Framework for Unified Software Debuggingcited by 35
  30. 2024Automatic Programming: Large Language Models and Beyondcited by 35
  31. 2024Exploration of LLM Multi-Agent Application Implementation Based on LangGraph+CrewAIcited by 35
  32. 2025GUARDIAN: Safeguarding LLM Multi-Agent Collaborations with Temporal Graph Modelingcited by 35
  33. 2023Automatic Code Summarization via ChatGPT: How Far Are We?cited by 34
  34. 2024SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model Agentscited by 34
  35. 2024Agent-Oriented Planning in Multi-Agent Systemscited by 34
  36. 2025CodeCoR: An LLM-Based Self-Reflective Multi-Agent Framework for Code Generationcited by 33
  37. 2024CodeTree: Agent-guided Tree Search for Code Generation with Large Language Modelscited by 32
  38. 2025From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Userscited by 32

50 most cited of 255 All 255 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey on Code Generation with LLM-based Agents
  2. 2026Vibe Coding: An Experiment with Test-Driven Development
  3. 2025Towards Advancing Code Generation with Large Language Models: A Research Roadmap
  4. 2023Self-planning Code Generation with Large Language Models
  5. 2025Evaluating Software Process Models for Multi-Agent Class-Level Code Generation
  6. 2023Think Outside the Code: Brainstorming Boosts Large Language Models in Code Generation
  7. 2023ChatDev: Communicative Agents for Software Development
  8. 2025BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution