mlsanityData to 7 Oct 2026

Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization

arXiv 2404.02183 ↗First posted 2 Apr 2024cs.SE cs.AI cs.CLcited by 84

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

Abstract (arXiv)

Recent advancements in automatic code generation using large language model (LLM) agent have brought us closer to the future of automated software development. However, existing single-agent approaches face limitations in generating and improving large-scale, complex codebases due to constraints in context length. To tackle this challenge, we propose Self-Organized multi-Agent framework (SoA), a novel multi-agent framework that enables the scalable and efficient generation and optimization of large-scale code. In SoA, self-organized agents operate independently to generate and modify code components while seamlessly collaborating to construct the overall codebase. A key feature of our framework is the automatic multiplication of agents based on problem complexity, allowing for dynamic scalability. This enables the overall code volume to be increased indefinitely according to the number of agents, while the amount of code managed by each agent remains constant. We evaluate SoA on the HumanEval benchmark and demonstrate that, compared to a single-agent system, each agent in SoA handles significantly less code, yet the overall generated code is substantially greater. Moreover, SoA surpasses the powerful single-agent baseline by 5% in terms of Pass@1 accuracy.

Key facts. Cited by 84 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. Builds on 13 of its 23 references that are in the map. First posted on arXiv 2 Apr 2024.

Builds on

13 of 23 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Self-collaboration Code Generation via ChatGPT15 Apr

Other references · 12

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  4. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  5. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  6. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  7. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Modelscited by 551
  8. 2022InCoder: A Generative Model for Code Infilling and Synthesiscited by 492
  9. 2023LooGLE: Can Long-Context Language Models Understand Long Contexts?cited by 200
  10. 2023ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understandingcited by 175
  11. 2024Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-stepcited by 123
  12. 2023Self-Edit: Fault-Aware Code Editor for Code Generationcited by 110

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 19; 2025: 40; 2026: 25.

84 papers.

Sort:

By area:

  1. 2024A Survey on Large Language Models for Code Generationcited by 646
  2. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMscited by 424
  3. 2024Large Language Model-Based Agents for Software Engineering: A Surveycited by 173
  4. 2025MultiAgentBench: Evaluating the Collaboration and Competition of LLM agentscited by 169
  5. 2024LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Aheadcited by 155
  6. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  7. 2024G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networkscited by 110
  8. 2024From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Futurecited by 85
  9. 2025MasRouter: Learning to Route LLMs for Multi-Agent Systemscited by 80
  10. 2024A Systematic Survey on Large Language Models for Algorithm Designcited by 65
  11. 2024Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Explorationcited by 58
  12. 2025G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systemscited by 56
38 more
  1. 2025A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasurescited by 54
  2. 2024Project Sid: Many-agent simulations toward AI civilizationcited by 46
  3. 2025A Survey on the Optimization of Large Language Model-based Agentscited by 45
  4. 2024Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent Systemcited by 40
  5. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 40
  6. 2026Code as Agent Harnesscited by 40
  7. 2025Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AIcited by 39
  8. 2025Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systemscited by 39
  9. 2024AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation through Static Analysis and Fuzz Testingcited by 34
  10. 2025Internet of Agents: Fundamentals, Applications, and Challengescited by 31
  11. 2025Adaptive Graph Pruning for Multi-Agent Communicationcited by 28
  12. 2024Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligencecited by 27
  13. 2024RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generationcited by 25
  14. 2025AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Predictioncited by 25
  15. 2025GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveragingcited by 25
  16. 2025Large Language Model-based Data Science Agent: A Surveycited by 22
  17. 2025Learning to Deliberate: Meta-policy Collaboration for Agentic LLMs with Multi-agent Reinforcement Learningcited by 18
  18. 2026Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judgecited by 16
  19. 2025Maestro: Learning to Collaborate via Conditional Listwise Policy Optimization for Multi-Agent LLMscited by 14
  20. 2025Self-Resource Allocation in Multi-Agent LLM Systemscited by 13
  21. 2025Visual Multi-Agent System: Mitigating Hallucination Snowballing via Visual Flowcited by 13
  22. 2024AutoPrep: Natural Language Question-Aware Data Preparation with a Multi-Agent Frameworkcited by 12
  23. 2025AgentInit: Initializing LLM-based Multi-Agent Systems via Diversity and Expertise Orchestration for Effective and Efficient Collaborationcited by 10
  24. 2026The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMscited by 10
  25. 2025Multi-agent systems for chemical engineering: A review and perspectivecited by 9
  26. 2026AgentConductor: Topology Evolution for Multi-Agent Competition-Level Code Generationcited by 9
  27. 2024From Text to Life: On the Reciprocal Relationship between Artificial Life and Large Language Modelscited by 8
  28. 2025Benchmarking LLMs' Swarm intelligencecited by 8
  29. 2025Distributional AGI Safetycited by 8
  30. 2026MetaGen: Self-Evolving Roles and Topologies for Multi-Agent LLM Reasoningcited by 8
  31. 2024INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulnesscited by 7
  32. 2026ChipBench: A Next-Step Benchmark for Evaluating LLM Performance in AI-Aided Chip Designcited by 7
  33. 2025AgentDropout: Dynamic Agent Elimination for Token-Efficient and High-Performance LLM-Based Multi-Agent Collaborationcited by 6
  34. 2025CodeVisionary: An Agent-based Framework for Evaluating Large Language Models in Code Generationcited by 6
  35. 2025Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstructioncited by 6
  36. 2025Is Your Benchmark Still Useful? Dynamic Benchmarking for Code Language Modelscited by 5
  37. 2025LLM-Agent-Controller: A Universal Multi-Agent Large Language Model System as a Control Engineercited by 5
  38. 2026PAC-BENCH: Evaluating Multi-Agent Collaboration under Privacy Constraintscited by 5

50 most cited of 84 All 84 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey on Code Generation with LLM-based Agents
  2. 2025AdaCoder: An Adaptive Planning and Multi-Agent Framework for Function-Level Code Generation
  3. 2025SEW: Self-Evolving Agentic Workflows for Automated Code Generation
  4. 2025CodeCoR: An LLM-Based Self-Reflective Multi-Agent Framework for Code Generation
  5. 2025Guided Code Generation with LLMs: A Multi-Agent Framework for Complex Code Tasks
  6. 2026SEMAG: Self-Evolutionary Multi-Agent Code Generation
  7. 2023AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation
  8. 2025Enhancing LLM Code Generation: A Systematic Evaluation of Multi-Agent Collaboration and Runtime Debugging for Improved Accuracy, Reliability, and Latency