mlsanityData to 7 Oct 2026

MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework

arXiv 2308.00352 ↗First posted 1 Aug 2023cs.AI cs.MAcited by 1,761

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs). Existing LLM-based multi-agent systems can already solve simple dialogue tasks. Solutions to more complex tasks, however, are complicated through logic inconsistencies due to cascading hallucinations caused by naively chaining LLMs. Here we introduce MetaGPT, an innovative meta-programming framework incorporating efficient human workflows into LLM-based multi-agent collaborations. MetaGPT encodes Standardized Operating Procedures (SOPs) into prompt sequences for more streamlined workflows, thus allowing agents with human-like domain expertise to verify intermediate results and reduce errors. MetaGPT utilizes an assembly line paradigm to assign diverse roles to various agents, efficiently breaking down complex tasks into subtasks involving many agents working together. On collaborative software engineering benchmarks, MetaGPT generates more coherent solutions than previous chat-based multi-agent systems. Our project can be found at https://github.com/geekan/MetaGPT

Key facts. Cited by 1,761 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 25 of its 46 references that are in the map. First posted on arXiv 1 Aug 2023.

Builds on

25 of 46 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration11 Jul
  2. 2023Building Cooperative Embodied Agents Modularly with Large Language Models5 Jul
  3. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents5 Jun
  4. 2023SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks27 May
  5. 2023Multi-Party Chat: Conversational Agents in Group Settings with Humans and Models26 Apr

Other references · 20

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  4. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  6. 2021Program Synthesis with Large Language Modelscited by 3,509
  7. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  8. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 1,908
  9. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  10. 2022Competition-Level Code Generation with AlphaCodecited by 1,427
  11. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  12. 2022InCoder: A Generative Model for Code Infilling and Synthesiscited by 492
8 more
  1. 2022CodeT: Code Generation with Generated Testscited by 369
  2. 2023CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-Xcited by 294
  3. 2023Large Language Models as Tool Makerscited by 293
  4. 2023LEVER: Learning to Verify Language-to-Code Generation with Executioncited by 228
  5. 2023Playing repeated games with Large Language Modelscited by 213
  6. 2023Errors are Useful Prompts: Instruction Guided Task Programming with Verifier-Assisted Iterative Promptingcited by 45
  7. 2023ChatLLM Network: More brains, More intelligencecited by 37
  8. 2021Latent Execution for Neural Program Synthesiscited by 35

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 63; 2024: 341; 2025: 523; 2026: 834.

1,761 papers.

Sort:

By area:

  1. 2023Qwen Technical Reportcited by 3,273
  2. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  3. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  4. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  5. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agentscited by 956
  6. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 752
  7. 2024A Survey on Large Language Models for Code Generationcited by 646
  8. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 622
  9. 2025Why Do Multi-Agent LLM Systems Fail?cited by 559
  10. 2024Executable Code Actions Elicit Better LLM Agentscited by 537
  11. 2023Cognitive Architectures for Language Agentscited by 422
  12. 2025Agent Laboratory: Using LLM Agents as Research Assistantscited by 405
38 more
  1. 2024AFlow: Automating Agentic Workflow Generationcited by 395
  2. 2024OS-ATLAS: A Foundation Action Model for Generalist GUI Agentscited by 370
  3. 2024Automated Design of Agentic Systemscited by 360
  4. 2024AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agentscited by 319
  5. 2024Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perceptioncited by 283
  6. 2024R-Judge: Benchmarking Safety Risk Awareness for LLM Agentscited by 268
  7. 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectivescited by 253
  8. 2024On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Surveycited by 240
  9. 2024Scaling Large Language Model-based Multi-Agent Collaborationcited by 235
  10. 2023DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Drivingcited by 233
  11. 2024Agent-as-a-Judge: Evaluate Agents with Agentscited by 223
  12. 2024Data Interpreter: An LLM Agent For Data Sciencecited by 222
  13. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewcited by 221
  14. 2024Magentic-One: A Generalist Multi-Agent System for Solving Complex Taskscited by 221
  15. 2023AutoAgents: A Framework for Automatic Agent Generationcited by 211
  16. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 206
  17. 2024Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalizationcited by 203
  18. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
  19. 2024APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasetscited by 188
  20. 2024Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaborationcited by 187
  21. 2023You Only Look at Screens: Multimodal Chain-of-Action Agentscited by 185
  22. 2024Agent S: An Open Agentic Framework that Uses Computers Like a Humancited by 182
  23. 2025AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Societycited by 180
  24. 2024More Agents Is All You Needcited by 174
  25. 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
  26. 2025Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systemscited by 170
  27. 2025AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challengescited by 167
  28. 2024The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Surveycited by 164
  29. 2024LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Aheadcited by 155
  30. 2023SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Modelscited by 151
  31. 2024Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fastcited by 149
  32. 2024UFO: A UI-Focused Agent for Windows OS Interactioncited by 147
  33. 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Reviewcited by 146
  34. 2025Prompt Injection Attack to Tool Selection in LLM Agentscited by 145
  35. 2023War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Warscited by 143
  36. 2023TaskBench: Benchmarking Large Language Models for Task Automationcited by 138
  37. 2023OpenAgents: An Open Platform for Language Agents in the Wildcited by 136
  38. 2024AutoDefense: Multi-Agent LLM Defense against Jailbreak Attackscited by 135

50 most cited of 1,761 All 1,761 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023MetaAgents: Large Language Model Based Agents for Decision-Making on Teaming
  2. 2026MetaGen: Self-Evolving Roles and Topologies for Multi-Agent LLM Reasoning
  3. 2026Understanding Conversational Patterns in Multi-agent Programming: A Case Study on Fibonacci Game Development
  4. 2026Developing LLM-based Multi-Agent Systems in Software Engineering: A Mixed-Method Experience Report
  5. 2026MASFactory: A Graph-centric Framework for Orchestrating LLM-Based Multi-Agent Systems with Vibe Graphing
  6. 2025Teamwork makes the dream work: LLMs-Based Agents for GitHub README.MD Summarization
  7. 2025AgentInit: Initializing LLM-based Multi-Agent Systems via Diversity and Expertise Orchestration for Effective and Efficient Collaboration
  8. 2025Enhancing LLM Performance Through Debate: An Empirical Study on Multi-Agent Debate for Coding Tasks