mlsanityData to 14 Oct 2026

Large Language Models Miss the Multi-Agent Mark

arXiv 2505.21298 ↗First posted 27 May 2025cs.MA cs.AI cs.LGcited by 26

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

Abstract (arXiv)

Recent interest in Multi-Agent Systems of Large Language Models (MAS LLMs) has led to an increase in frameworks leveraging multiple LLMs to tackle complex tasks. However, much of this literature appropriates the terminology of MAS without engaging with its foundational principles. In this position paper, we highlight critical discrepancies between MAS theory and current MAS LLMs implementations, focusing on four key areas: the social aspect of agency, environment design, coordination and communication protocols, and measuring emergent behaviours. Our position is that many MAS LLMs lack multi-agent characteristics such as autonomy, social interaction, and structured environments, and often rely on oversimplified, LLM-centric architectures. The field may slow down and lose traction by revisiting problems the MAS literature has already addressed. Therefore, we systematically analyse this issue and outline associated research opportunities; we advocate for better integrating established MAS concepts and more precise terminology to avoid mischaracterisation and missed opportunities.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 49 of its 114 references that are in the map. First posted on arXiv 27 May 2025.

Builds on

49 of 114 references.

Closest ancestors · 12

Same direction, newest first

  1. 2025Nexus: A Lightweight and Scalable Multi-Agent Framework for Complex Tasks Automation26 Feb
  2. 2025Beyond Text: Implementing Multimodal Large Language Model-Powered Multi-Agent Systems Using a No-Code Platform1 Jan
  3. 2024Asynchronous Tool Usage for Real-Time Agents28 Oct
  4. 2024Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance16 Oct
  5. 2024Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems3 Oct
  6. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challenges21 Jan
  7. 2023Theory of Mind for Multi-Agent Collaboration via Large Language Models16 Oct
  8. 2023Agents: An Open-source Framework for Autonomous Language Agents14 Sep
  9. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors21 Aug
  10. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate14 Aug
  11. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework1 Aug
  12. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents5 Jun

Other references · 37

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2020Scaling Laws for Neural Language Modelscited by 6,586
  5. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  6. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  7. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  8. 2023Large Language Modelscited by 780
  9. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 634
  10. 2024AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Basescited by 429
  11. 2023Large Language Models Fail on Trivial Alterations to Theory-of-Mind Taskscited by 292
  12. 2023Self-collaboration Code Generation via ChatGPTcited by 258
25 more
  1. 2023Exploring Large Language Models for Communication Games: An Empirical Study on Werewolfcited by 241
  2. 2023S3: Social-network Simulation System with Large Language Model-Empowered Agentscited by 233
  3. 2023Evaluating Large Language Models in Theory of Mind Taskscited by 222
  4. 2019Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutionscited by 192
  5. 2021Open-Ended Learning Leads to Generally Capable Agentscited by 182
  6. 2023RoCo: Dialectic Multi-Robot Collaboration with Large Language Modelscited by 172
  7. 2020Emergent Multi-Agent Communication in the Deep Learning Eracited by 170
  8. 2023Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Modelscited by 163
  9. 2023An Empirical Study of the Non-determinism of ChatGPT in Code Generationcited by 137
  10. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAGcited by 123
  11. 2022SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learningcited by 122
  12. 2023Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems?cited by 106
  13. 2019Open-ended Learning in Symmetric Zero-sum Gamescited by 96
  14. 2025Multiagent Finetuning: Self Improvement with Diverse Reasoning Chainscited by 95
  15. 2023Collaborating with language models for embodied reasoningcited by 61
  16. 2023Theory of Mind in Large Language Models: Examining Performance of 11 State-of-the-Art models vs. Children Aged 7-10 on Advanced Testscited by 48
  17. 2023Welfare Diplomacy: Benchmarking Language Model Cooperationcited by 45
  18. 2024A Scalable Communication Protocol for Networks of Large Language Modelscited by 45
  19. 2019Emergent Linguistic Phenomena in Multi-Agent Communication Gamescited by 36
  20. 2024Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learningcited by 33
  21. 2023Interactive Planning Using Large Language Models for Partially Observable Robotics Taskscited by 27
  22. 2024The Unreasonable Effectiveness of Eccentric Automatic Promptscited by 12
  23. 2023Exploring the Problems, their Causes and Solutions of AI Pair Programming: A Study on GitHub and Stack Overflowcited by 11
  24. 2023Language Models as a Service: Overview of a New Paradigm and its Challengescited by 10
  25. 2022Formalizing the Problem of Side Effect Regularizationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 6; 2026: 20.

26 papers.

Sort:

By area:

  1. 2025Group size effects and collective misalignment in LLM multi-agent systemscited by 16
  2. 2026Dual Latent Memory for Visual Multi-agent Systemcited by 10
  3. 2026Generative AI collective behavior needs an interactionist paradigmcited by 6
  4. 2026AI Organizations are More Effective but Less Aligned than Individual Agentscited by 5
  5. 2026Social Theory Should Be a Structural Prior for Agentic AI: A Formal Framework for Multi-Agent Social Systemscited by 5
  6. 2026MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMscited by 5
  7. 2026When Parallelism Pays Off: Cohesion-Aware Task Partitioning for Multi-Agent Codingcited by 5
  8. 2025Parallelism Meets Adaptiveness: Scalable Documents Understanding in Multi-Agent LLM Systemscited by 4
  9. 2025How large language models judge and influence human cooperationcited by 3
  10. 2026When Do Multi-Agent Systems Outperform? Analysing the Learning Efficiency of Agentic Systemscited by 2
  11. 2026Do Agent Societies Develop Intellectual Elites? The Hidden Power Laws of Collective Cognition in LLM Multi-Agent Systemscited by 2
  12. 2025The Hunger Game Debate: On the Emergence of Over-Competition in Multi-Agent Systemscited by 1
14 more
  1. 2025Towards Ethical Multi-Agent Systems of Large Language Models: A Mechanistic Interpretability Perspectivecited by 1
  2. 2026Discoverable Agent Knowledge -- A Formal Framework for Agentic KG Affordances (Extended Version)cited by 1
  3. 2026MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordinationcited by 1
  4. 2026Competitive Market Behavior of LLMscited by 1
  5. 2025Single-Agent Scaling Fails Multi-Agent Intelligence: Towards Foundation Models with Native Multi-Agent Intelligencecited by 0
  6. 2026Towards a Science of Collective AI: LLM-based Multi-Agent Systems Need a Transition from Blind Trial-and-Error to Rigorous Sciencecited by 0
  7. 2026Artificial Organisationscited by 0
  8. 2026Agentic Social Affordance Framework (ASAF): Agent Identity Design as a Collaboration Interface in Multi-Agent Systemscited by 0
  9. 2026AgentRadio: Passive Awareness for Long-Horizon Multi-Agent Collaborationcited by 0
  10. 2026How a shared state is described determines whether AI agents synchronizecited by 0
  11. 2026An Investigation of the NeurIPS and ICML 2025 Position Trackscited by 0
  12. 2026Epistemic-Probabilistic Model for Guarded Multi-Agent LLM Coordinationcited by 0
  13. 2026LLMs for Executable Multi-Agent System Specification Generationcited by 0
  14. 2026A Society of Researchers: Designing Institutions for Populations of Autonomous Research Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challenges
  2. 2025Contemporary Agent Technology: LLM-Driven Advancements vs Classic Multi-Agent Systems
  3. 2024A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Application
  4. 2026LLM-Enabled Multi-Agent Systems: Empirical Evaluation and Insights into Emerging Design Patterns & Paradigms
  5. 2025LLMs Working in Harmony: A Survey on the Technological Aspects of Building Effective LLM-Based Multi Agent Systems
  6. 2026Multi-User Large Language Model Agents
  7. 2024LLM-Augmented Agent-Based Modelling for Social Simulations: Challenges and Opportunities
  8. 2025Literature Review Of Multi-Agent Debate For Problem-Solving