mlsanityData to 7 Oct 2026

Multi-Agent Collaboration Mechanisms: A Survey of LLMs

arXiv 2501.06322 ↗First posted 10 Jan 2025cs.AIcited by 424

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

Abstract (arXiv)

With recent advances in Large Language Models (LLMs), Agentic AI has become phenomenal in real-world applications, moving toward multiple LLM-based agents to perceive, learn, reason, and act collaboratively. These LLM-based Multi-Agent Systems (MASs) enable groups of intelligent agents to coordinate and solve complex tasks collectively at scale, transitioning from isolated models to collaboration-centric approaches. This work provides an extensive survey of the collaborative aspect of MASs and introduces an extensible framework to guide future research. Our framework characterizes collaboration mechanisms based on key dimensions: actors (agents involved), types (e.g., cooperation, competition, or coopetition), structures (e.g., peer-to-peer, centralized, or distributed), strategies (e.g., role-based or model-based), and coordination protocols. Through a review of existing methodologies, our findings serve as a foundation for demystifying and advancing LLM-based MASs toward more intelligent and collaborative solutions for complex, real-world use cases. In addition, various applications of MASs across diverse domains, including 5G/6G networks, Industry 5.0, question answering, and social and cultural settings, are also investigated, demonstrating their wider adoption and broader impacts. Finally, we identify key lessons learned, open challenges, and potential research directions of MASs towards artificial collective intelligence.

Key facts. Cited by 424 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 90 of its 143 references that are in the map. First posted on arXiv 10 Jan 2025.

Builds on

90 of 143 references.

Closest ancestors · 21

Same direction, newest first

  1. 2024Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks7 Nov
  2. 2024Advancing Agentic Systems: Dynamic Task Decomposition, Tool Integration and Evaluation using Novel Metrics and Dataset29 Oct
  3. 2024AgentSense: Benchmarking Social Intelligence of Language Agents through Interactive Scenarios25 Oct
  4. 2024Agent-as-a-Judge: Evaluate Agents with Agents14 Oct
  5. 2024(Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts20 May
  6. 2024Testing and Understanding Erroneous Planning in LLM Agents through Synthesized User Inputs27 Apr
  7. 2024AgentCoord: Visually Exploring Coordination Strategy for LLM-based Multi-Agent Collaboration18 Apr
  8. 2024Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?28 Feb
  9. 2024Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation18 Feb
  10. 2024Understanding the planning of LLM agents: A survey5 Feb
  11. 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives19 Dec
  12. 2023Towards Reasoning in Large Language Models via Multi-Agent Peer Review Collaboration14 Nov
9 more
  1. 2023A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration3 Oct
  2. 2023AutoAgents: A Framework for Automatic Agent Generation29 Sep
  3. 2023The Rise and Potential of Large Language Model Based Agents: A Survey14 Sep
  4. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate14 Aug
  5. 2023Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration11 Jul
  6. 2023Inferring the Goals of Communicating Agents from Actions and Instructions28 Jun
  7. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents5 Jun
  8. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society31 Mar
  9. 2023Harms from Increasingly Agentic Algorithmic Systems20 Feb

Other references · 69

  1. 2017Attention Is All You Needcited by 59,932
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2020Scaling Laws for Neural Language Modelscited by 6,411
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  5. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  6. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  7. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,615
  8. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  9. 2024Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preferencecited by 1,151
  10. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  11. 2023ChatDev: Communicative Agents for Software Developmentcited by 893
  12. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 622
38 more
  1. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 550
  2. 2023Are Emergent Abilities of Large Language Models a Mirage?cited by 515
  3. 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studiescited by 506
  4. 2021Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Surveycited by 457
  5. 2023MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoningcited by 311
  6. 2024The Power of Noise: Redefining Retrieval for RAG Systemscited by 275
  7. 2021AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Promptscited by 265
  8. 2024Frontier Models are Capable of In-context Schemingcited by 252
  9. 2024A Survey on Mixture of Experts in Large Language Modelscited by 233
  10. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewcited by 221
  11. 2023Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attackscited by 189
  12. 2024MapCoder: Multi-Agent Code Generation for Competitive Problem Solvingcited by 177
  13. 2020Open Problems in Cooperative AIcited by 167
  14. 2022Thinking Fast and Slow in Large Language Modelscited by 136
  15. 2023AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systemscited by 116
  16. 2024Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffoldingcited by 115
  17. 2023Mindstorms in Natural Language-Based Societies of Mindcited by 105
  18. 2023Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generationcited by 103
  19. 2024MARG: Multi-Agent Review Generation for Scientific Paperscited by 98
  20. 2023Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debatecited by 94
  21. 2023Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiationcited by 94
  22. 2024AgentInstruct: Toward Generative Teaching with Agentic Flowscited by 88
  23. 2024Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimizationcited by 84
  24. 2024AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planningcited by 81
  25. 2024PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safetycited by 79
  26. 2023Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communicationcited by 78
  27. 2023FedExP: Speeding Up Federated Averaging via Extrapolationcited by 68
  28. 2023CompeteAI: Understanding the Competition Dynamics in Large Language Model-based Agentscited by 65
  29. 2023Federated Learning of Gboard Language Models with Differential Privacycited by 64
  30. 2024Is this the real life? Is this just fantasy? The Misleading Success of Simulating Social Interactions With LLMscited by 59
  31. 2024MACRec: a Multi-Agent Collaboration Framework for Recommendationcited by 58
  32. 2023A Bibliometric Review of Large Language Models Research from 2017 to 2023cited by 56
  33. 2023MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaborationcited by 56
  34. 2023Large Language Models Empowered Autonomous Edge AI for Connected Intelligencecited by 55
  35. 2023Large Language Model Enhanced Multi-Agent Systems for 6G Communicationscited by 53
  36. 2024Large Language Models Assume People are More Rational than We Really arecited by 49
  37. 2024Evaluating Language Model Agency through Negotiationscited by 43
  38. 2024Evaluating Cultural and Social Awareness of LLM Web Agentscited by 43

50 most cited of 69 All 69 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 203; 2026: 221.

424 papers.

Sort:

By area:

  1. 2025AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challengescited by 167
  2. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  3. 2025Towards a Science of Scaling Agent Systemscited by 125
  4. 2025A Survey of Context Engineering for Large Language Modelscited by 120
  5. 2025Where LLM Agents Fail and How They can Learn From Failurescited by 118
  6. 2025A survey of agent interoperability protocols: Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent-to-Agent Protocol (A2A), and Agent Network Protocol (ANP)cited by 98
  7. 2025Harnessing Multiple Large Language Models: A Survey on LLM Ensemblecited by 86
  8. 2025MemEvolve: Meta-Evolution of Agent Memory Systemscited by 81
  9. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discoverycited by 74
  10. 2025Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?cited by 74
  11. 2025Latent Collaboration in Multi-Agent Systemscited by 67
  12. 2025Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debatecited by 63
38 more
  1. 2025TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systemscited by 58
  2. 2025From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents Workflowscited by 57
  3. 2025Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Controlcited by 56
  4. 2025GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoningcited by 56
  5. 2025Cache-to-Cache: Direct Semantic Communication Between Large Language Modelscited by 54
  6. 2025LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directionscited by 49
  7. 2025Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directionscited by 46
  8. 2025SAGA: A Security Architecture for Governing AI Agentic Systemscited by 45
  9. 2025Agentic Web: Weaving the Next Web with AI Agentscited by 43
  10. 2025BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attackscited by 37
  11. 2025KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systemscited by 35
  12. 2025Measuring Agents in Productioncited by 35
  13. 2025PersonaX: A Recommendation Agent Oriented User Modeling Framework for Long Behavior Sequencecited by 33
  14. 2025LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospectscited by 31
  15. 2025Internet of Agents: Fundamentals, Applications, and Challengescited by 31
  16. 2025Enabling Agents to Communicate Entirely in Latent Spacecited by 31
  17. 2025ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Taskscited by 30
  18. 2025MedAgentBoard: Benchmarking Multi-Agent Collaboration with Conventional Methods for Diverse Medical Taskscited by 29
  19. 2025LLM-Based Human-Agent Collaboration and Interaction Systems: A Surveycited by 28
  20. 2025Thought Communication in Multiagent Collaborationcited by 28
  21. 2025A Comprehensive Survey on Multi-Agent Cooperative Decision-Making: Scenarios, Approaches, Challenges and Perspectivescited by 27
  22. 2025Debate Only When Necessary: Adaptive Multiagent Collaboration for Efficient LLM Reasoningcited by 27
  23. 2025We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systemscited by 27
  24. 2025CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewardscited by 27
  25. 2025PiFlow: Principle-Aware Scientific Discovery with Multi-Agent Collaborationcited by 25
  26. 2025LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarioscited by 25
  27. 2025Creativity in LLM-based Multi-Agent Systems: A Surveycited by 23
  28. 2025Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunitiescited by 23
  29. 2026Reinforcing Chain-of-Thought Reasoning with Self-Evolving Rubricscited by 23
  30. 2026AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaborationcited by 23
  31. 2025Group Think: Multiple Concurrent Reasoning Agents Collaborating at Token Level Granularitycited by 22
  32. 2026From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agentscited by 22
  33. 2025When Identity Skews Debate: Anonymization for Bias-Reduced Multi-Agent Reasoningcited by 20
  34. 2026RealMem: Benchmarking LLMs in Real-World Memory-Driven Interactioncited by 20
  35. 2025Agentic AI Needs a Systems Theorycited by 19
  36. 2025NLI4VolVis: Natural Language Interaction for Volume Visualization via LLM Multi-Agents and Editable 3D Gaussian Splattingcited by 19
  37. 2025Aegis: Automated Error Generation and Attribution for Multi-Agent Systemscited by 19
  38. 2025COMPASS: Enhancing Agent Long-Horizon Reasoning with Evolving Contextcited by 19

50 most cited of 424 All 424 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025LLMs Working in Harmony: A Survey on the Technological Aspects of Building Effective LLM-Based Multi Agent Systems
  2. 2024A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Application
  3. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challenges
  4. 2025Collaborate, Deliberate, Evaluate: How LLM Alignment Affects Coordinated Multi-Agent Outcomes
  5. 2025Beyond Self-Talk: A Communication-Centric Survey of LLM-Based Multi-Agent Systems
  6. 2024LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions
  7. 2024Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects
  8. 2025Literature Review Of Multi-Agent Debate For Problem-Solving