mlsanityData to 7 Oct 2026

Scaling Large Language Model-based Multi-Agent Collaboration

arXiv 2406.07155 ↗First posted 11 Jun 2024cs.AI cs.CL cs.MAcited by 235

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

Abstract (arXiv)

Recent breakthroughs in large language model-driven autonomous agents have revealed that multi-agent collaboration often surpasses each individual through collective reasoning. Inspired by the neural scaling law--increasing neurons enhances performance, this study explores whether the continuous addition of collaborative agents can yield similar benefits. Technically, we utilize directed acyclic graphs to organize agents into a multi-agent collaboration network (MacNet), upon which their interactive reasoning is topologically orchestrated for autonomous task solving. Extensive evaluations reveal that it effectively supports collaboration among over a thousand agents, with irregular topologies outperforming regular ones. We also identify a collaborative scaling law--the overall performance follows a logistic growth pattern as agents scale, with collaborative emergence occurring earlier than traditional neural emergence. We speculate this may be because scaling agents catalyzes their multidimensional considerations during interactive reflection and refinement, thereby producing more comprehensive artifacts. The code is available at https://github.com/OpenBMB/ChatDev/tree/macnet.

Key facts. Cited by 235 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 70 of its 112 references that are in the map. First posted on arXiv 11 Jun 2024.

Builds on

70 of 112 references.

Closest ancestors · 19

Same direction, newest first

  1. 2024Iterative Experience Refinement of Software-Developing Agents7 May
  2. 2024CoMM: Collaborative Multi-Agent, Multi-Reasoning-Path Prompting for Complex Problem Solving26 Apr
  3. 2024Embodied LLM Agents Learn to Cooperate in Organized Teams19 Mar
  4. 2024Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?28 Feb
  5. 2024Language Agents as Optimizable Graphs26 Feb
  6. 2024Professional Agents -- Evolving Large Language Models into Autonomous Experts with Human-Level Competencies6 Feb
  7. 2024More Agents Is All You Need3 Feb
  8. 2023Experiential Co-Learning of Software-Developing Agents28 Dec
  9. 2023Controlling Large Language Model-based Agents for Large-Scale Decision-Making: An Actor-Critic Approach23 Nov
  10. 2023Agents: An Open-source Framework for Autonomous Language Agents14 Sep
  11. 2023Cognitive Architectures for Language Agents5 Sep
  12. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors21 Aug
7 more
  1. 2023ExpeL: LLM Agents Are Experiential Learners20 Aug
  2. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate14 Aug
  3. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework1 Aug
  4. 2023Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration11 Jul
  5. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents5 Jun
  6. 2023SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks27 May
  7. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society31 Mar

Other references · 51

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  6. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  7. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  8. 2020Scaling Laws for Neural Language Modelscited by 6,411
  9. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  10. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  11. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  12. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
38 more
  1. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  2. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  3. 2022Emergent Abilities of Large Language Modelscited by 2,483
  4. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  5. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  6. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,173
  7. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  8. 2023ChatDev: Communicative Agents for Software Developmentcited by 893
  9. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 873
  10. 2023Large Language Models as Optimizerscited by 830
  11. 2022Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Modelcited by 557
  12. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 550
  13. 2023Are Emergent Abilities of Large Language Models a Mirage?cited by 515
  14. 2023Scaling Data-Constrained Language Modelscited by 391
  15. 2023MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoningcited by 311
  16. 2023Large Language Models are Effective Text Rankers with Pairwise Ranking Promptingcited by 302
  17. 2023ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMscited by 297
  18. 2024Quiet-STaR: Language Models Can Teach Themselves to Think Before Speakingcited by 292
  19. 2023Role-Play with Large Language Modelscited by 290
  20. 2024Debating with More Persuasive LLMs Leads to More Truthful Answerscited by 255
  21. 2023Large Language Models as Commonsense Knowledge for Large-Scale Task Planningcited by 231
  22. 2024Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agentscited by 210
  23. 2024ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Modelscited by 200
  24. 2023RoCo: Dialectic Multi-Robot Collaboration with Large Language Modelscited by 171
  25. 2023LM vs LM: Detecting Factual Errors via Cross Examinationcited by 155
  26. 2023EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activitiescited by 154
  27. 2023War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Warscited by 143
  28. 2024Observational Scaling Laws and the Predictability of Language Model Performancecited by 128
  29. 2023Retrieval meets Long Context Large Language Modelscited by 114
  30. 2023Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems?cited by 104
  31. 2023ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Searchcited by 103
  32. 2024AIOS: LLM Agent Operating Systemcited by 94
  33. 2023On Generative Agents in Recommendationcited by 88
  34. 2023MetaAgents: Large Language Model Based Agents for Decision-Making on Teamingcited by 85
  35. 2023Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communicationcited by 78
  36. 2023Training Socially Aligned Language Models on Simulated Social Interactionscited by 77
  37. 2024Demystifying Chains, Trees, and Graphs of Thoughtscited by 63
  38. 2023GameGPT: Multi-agent Collaborative Framework for Game Developmentcited by 41

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 21; 2025: 85; 2026: 129.

235 papers.

Sort:

By area:

  1. 2024Automated Design of Agentic Systemscited by 360
  2. 2024Agent-as-a-Judge: Evaluate Agents with Agentscited by 223
  3. 2025A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?cited by 215
  4. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
  5. 2025MultiAgentBench: Evaluating the Collaboration and Competition of LLM agentscited by 169
  6. 2025Multi-agent Architecture Search via Agentic Supernetcited by 164
  7. 2024Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systemscited by 129
  8. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  9. 2025Towards a Science of Scaling Agent Systemscited by 125
  10. 2025G-Memory: Tracing Hierarchical Memory for Multi-Agent Systemscited by 112
  11. 2024G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networkscited by 110
  12. 2025Multi-Agent Design: Optimizing Agents with Better Prompts and Topologiescited by 106
38 more
  1. 2025Multi-Agent Collaboration via Evolving Orchestrationcited by 102
  2. 2024On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agentscited by 92
  3. 2024From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agentscited by 76
  4. 2024A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Applicationcited by 54
  5. 2024Knowledge Mechanisms in Large Language Models: A Survey and Perspectivecited by 50
  6. 2024Internal Consistency and Self-Feedback in Large Language Models: A Surveycited by 49
  7. 2025EvoFlow: Evolving Diverse Agentic Workflows On The Flycited by 49
  8. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  9. 2025MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systemscited by 45
  10. 2025Stop Overvaluing Multi-Agent Debate -- We Must Rethink Evaluation and Embrace Model Heterogeneitycited by 43
  11. 2024Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent Systemcited by 40
  12. 2025Multi-agent Embodied AI: Advances and Future Directionscited by 36
  13. 2025GUARDIAN: Safeguarding LLM Multi-Agent Collaborations with Temporal Graph Modelingcited by 35
  14. 2025X-MAS: Towards Building Multi-Agent Systems with Heterogeneous LLMscited by 33
  15. 2025Flow: Modularized Agentic Workflow Automationcited by 31
  16. 2025Internet of Agents: Fundamentals, Applications, and Challengescited by 31
  17. 2025AgentsNet: Coordination and Collaborative Reasoning in Multi-Agent LLMscited by 31
  18. 2024Multi-Agent Collaboration via Cross-Team Orchestrationcited by 30
  19. 2024SMoA: Improving Multi-agent Large Language Models with Sparse Mixture-of-Agentscited by 30
  20. 2025ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Taskscited by 30
  21. 2025A Survey of Optimization Modeling Meets LLMs: Progress and Future Directionscited by 30
  22. 2025Adaptive Graph Pruning for Multi-Agent Communicationcited by 28
  23. 2025CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewardscited by 27
  24. 2024Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trendscited by 26
  25. 2026MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarkscited by 26
  26. 2024AgentMove: A Large Language Model based Agentic Framework for Zero-shot Next Location Predictioncited by 25
  27. 2025MDTeamGPT: A Self-Evolving LLM-based Multi-Agent Framework for Multi-Disciplinary Team Medical Consultationcited by 25
  28. 2025AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Predictioncited by 25
  29. 2025Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunitiescited by 23
  30. 2024Synthesizing Post-Training Data for LLMs through Multi-Agent Simulationcited by 22
  31. 2024LLMs Can Simulate Standardized Patients via Agent Coevolutioncited by 22
  32. 2025Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systemscited by 22
  33. 2025OptimAI: Optimization from Natural Language Using LLM-Powered AI Agentscited by 22
  34. 2026From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agentscited by 22
  35. 2025Do We Truly Need So Many Samples? Multi-LLM Repeated Sampling Efficiently Scales Test-Time Computecited by 20
  36. 2025AI Scientists Fail Without Strong Implementation Capabilitycited by 20
  37. 2025Intrinsic Memory Agents: Heterogeneous Multi-Agent LLM Systems through Structured Contextual Memorycited by 19
  38. 2025Aegis: Automated Error Generation and Attribution for Multi-Agent Systemscited by 19

50 most cited of 235 All 235 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Can Small Agents Collaborate to Beat a Single Large Language Model?
  2. 2026Scaling Behavior of Single LLM-Driven Multi-Agent Systems
  3. 2025Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning
  4. 2026DIG to Heal: Scaling General-purpose Agent Collaboration via Explainable Dynamic Decision Paths
  5. 2025Self-Evolving Multi-Agent Systems via Textual Backpropagation
  6. 2026Brain-Inspired Graph Multi-Agent Systems for LLM Reasoning
  7. 2025Single-Agent Scaling Fails Multi-Agent Intelligence: Towards Foundation Models with Native Multi-Agent Intelligence
  8. 2025Synchronization Dynamics of Heterogeneous, Collaborative Multi-Agent AI Systems