mlsanityData to 7 Oct 2026

LLM Multi-Agent Systems: Challenges and Open Problems

arXiv 2402.03578 ↗First posted 5 Feb 2024cs.MA cs.AIcited by 119

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

Abstract (arXiv)

This paper explores multi-agent systems and identify challenges that remain inadequately addressed. By leveraging the diverse capabilities and roles of individual agents, multi-agent systems can tackle complex tasks through agent collaboration. We discuss optimizing task allocation, fostering robust reasoning through iterative debates, managing complex and layered context information, and enhancing memory management to support the intricate interactions within multi-agent systems. We also explore potential applications of multi-agent systems in blockchain systems to shed light on their future development and application in real-world distributed systems.

Key facts. Cited by 119 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 28 of its 43 references that are in the map. First posted on arXiv 5 Feb 2024.

Builds on

28 of 43 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security10 Jan
  2. 2023Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents20 Nov
  3. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate14 Aug
  4. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents5 Jun

Other references · 24

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  4. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  5. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  6. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 1,908
  7. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  8. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  9. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  10. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  11. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 873
  12. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 871
12 more
  1. 2023Large Language Models as Tool Makerscited by 293
  2. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewcited by 221
  3. 2023Large Language Model Guided Tree-of-Thoughtcited by 218
  4. 2023Augmenting Language Models with Long-Term Memorycited by 186
  5. 2022Rationale-Augmented Ensembles in Language Modelscited by 111
  6. 2023Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems?cited by 104
  7. 2023Tab-CoT: Zero-shot Tabular Chain of Thoughtcited by 42
  8. 2023CGMI: Configurable General Multi-Agent Interaction Frameworkcited by 41
  9. 2023MoT: Memory-of-Thought Enables ChatGPT to Self-Improvecited by 37
  10. 2019Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learningcited by 32
  11. 2023Prompt-Guided Retrieval Augmentation for Non-Knowledge-Intensive Taskscited by 21
  12. 2022Oracles & Followers: Stackelberg Equilibria in Deep Multi-Agent Reinforcement Learningcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 17; 2025: 71; 2026: 31.

119 papers.

Sort:

By area:

  1. 2025AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agentscited by 196
  2. 2024Large Language Model-Brained GUI Agents: A Surveycited by 160
  3. 2024Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systemscited by 129
  4. 2024Determinants of LLM-assisted Decision-Makingcited by 55
  5. 2024Internal Consistency and Self-Feedback in Large Language Models: A Surveycited by 49
  6. 2025SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoningcited by 41
  7. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 40
  8. 2025UFO2: The Desktop AgentOScited by 38
  9. 2025PathFinder: A Multi-Modal Multi-Agent System for Medical Diagnostic Decision-Making Applied to Histopathologycited by 36
  10. 2025Who is Introducing the Failure? Automatically Attributing Failures of Multi-Agent Systems via Spectrum Analysiscited by 33
  11. 2025From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Userscited by 32
  12. 2025ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Taskscited by 30
38 more
  1. 2025Shifting AI Efficiency From Model-Centric to Data-Centric Compressioncited by 29
  2. 2024Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligencecited by 27
  3. 2024From Sora What We Can See: A Survey of Text-to-Video Generationcited by 26
  4. 2025Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunitiescited by 23
  5. 2024Reinforcement Learning from Multi-role Debates as Feedback for Bias Mitigation in LLMscited by 22
  6. 2024BattleAgent: Multi-modal Dynamic Emulation on Historical Battles to Complement Historical Analysiscited by 20
  7. 2026Large Language Model Reasoning Failurescited by 20
  8. 2024Towards Effective GenAI Multi-Agent Collaboration: Design and Evaluation for Enterprise Applicationscited by 19
  9. 2025Talk Structurally, Act Hierarchically: A Collaborative Framework for LLM Multi-Agent Systemscited by 17
  10. 2025Securing GenAI Multi-Agent Systems Against Tool Squatting: A Zero Trust Registry-Based Approachcited by 17
  11. 2025Agent-X: Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Taskscited by 17
  12. 2026Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance Graphscited by 17
  13. 2024MorphAgent: Empowering Agents through Self-Evolving Profiles and Decentralized Collaborationcited by 15
  14. 2025P2P: Automated Paper-to-Poster Generation and Fine-Grained Benchmarkcited by 15
  15. 2025LLM DNA: Tracing Model Evolution via Functional Representationscited by 15
  16. 2025ParallelMuse: Agentic Parallel Thinking for Deep Information Seekingcited by 14
  17. 2025CoLMDriver: LLM-based Negotiation Benefits Cooperative Autonomous Drivingcited by 13
  18. 2025Self-Resource Allocation in Multi-Agent LLM Systemscited by 13
  19. 2025Agentic AI Systems Applied to tasks in Financial Services: Modeling and model risk management crewscited by 12
  20. 2025Learning from Diverse Reasoning Paths with Routing and Collaborationcited by 12
  21. 2026AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agentcited by 12
  22. 2024I Want to Break Free! Persuasion and Anti-Social Behavior of LLMs in Multi-Agent Settings with Social Hierarchycited by 11
  23. 2026TrajAudit: Automated Failure Diagnosis for Agentic Coding Systemscited by 11
  24. 2025Cognitive Edge Computing: A Comprehensive Survey on Optimizing Large Models and AI Agents for Pervasive Deploymentcited by 10
  25. 2025LLMs Working in Harmony: A Survey on the Technological Aspects of Building Effective LLM-Based Multi Agent Systemscited by 10
  26. 2025Synergizing Logical Reasoning, Knowledge Management and Collaboration in Multi-Agent LLM Systemcited by 10
  27. 2025FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Datacited by 10
  28. 2025Aurelia: Test-time Reasoning Distillation in Audio-Visual LLMscited by 9
  29. 2025A Call for Collaborative Intelligence: Why Human-Agent Systems Should Precede AI Autonomycited by 9
  30. 2025Multi-agent systems for chemical engineering: A review and perspectivecited by 9
  31. 2025A Lightweight Large Language Model-Based Multi-Agent System for 2D Frame Structural Analysiscited by 9
  32. 2025FunReason-MT Technical Report: Advanced Data Synthesis Solution for Real-world Multi-Turn Tool-usecited by 9
  33. 2025Multi-Actor Generative Artificial Intelligence as a Game Enginecited by 8
  34. 2025S-DAG: A Subject-Based Directed Acyclic Graph for Multi-Agent Heterogeneous Reasoningcited by 8
  35. 2024TurtleBench: Evaluating Top Language Models via Real-World Yes/No Puzzlescited by 7
  36. 2025BetaWeb: Towards a Blockchain-enabled Trustworthy Agentic Webcited by 7
  37. 2025Fundamentals of Building Autonomous LLM Agentscited by 7
  38. 2025Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignmentcited by 7

50 most cited of 119 All 119 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Towards Transparent and Incentive-Compatible Collaboration in Decentralized LLM Multi-Agent Systems: A Blockchain-Driven Approach
  2. 2025Beyond Self-Talk: A Communication-Centric Survey of LLM-Based Multi-Agent Systems
  3. 2025Seven Security Challenges in Cross-domain Multi-agent LLM Systems
  4. 2025Fetch.ai: An Architecture for Modern Multi-Agent Systems
  5. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMs
  6. 2025Enabling Regulatory Multi-Agent Collaboration: Architecture, Challenges, and Solutions
  7. 2026LLM-Enabled Multi-Agent Systems: Empirical Evaluation and Insights into Emerging Design Patterns & Paradigms
  8. 2025AgentsNet: Coordination and Collaborative Reasoning in Multi-Agent LLMs