# Large Language Models Miss the Multi-Agent Mark

arXiv: https://arxiv.org/abs/2505.21298 · HTML: https://mlsanity.com/paper/2505.21298/

## 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.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 49)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https://mlsanity.com/paper/2308.10848/) (2023)
- [AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases](https://mlsanity.com/paper/2407.12784/) (2024)
- [Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents](https://mlsanity.com/paper/2306.03314/) (2023)
- [Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks](https://mlsanity.com/paper/2302.08399/) (2023)
- [Self-collaboration Code Generation via ChatGPT](https://mlsanity.com/paper/2304.07590/) (2023)
- [Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf](https://mlsanity.com/paper/2309.04658/) (2023)
- [S3: Social-network Simulation System with Large Language Model-Empowered Agents](https://mlsanity.com/paper/2307.14984/) (2023)
- [Evaluating Large Language Models in Theory of Mind Tasks](https://mlsanity.com/paper/2302.02083/) (2023)
- [Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions](https://mlsanity.com/paper/1901.01753/) (2019)
- [Open-Ended Learning Leads to Generally Capable Agents](https://mlsanity.com/paper/2107.12808/) (2021)
- [RoCo: Dialectic Multi-Robot Collaboration with Large Language Models](https://mlsanity.com/paper/2307.04738/) (2023)
- [Emergent Multi-Agent Communication in the Deep Learning Era](https://mlsanity.com/paper/2006.02419/) (2020)
- [Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models](https://mlsanity.com/paper/2305.14763/) (2023)
- [Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2410.02506/) (2024)
- [An Empirical Study of the Non-determinism of ChatGPT in Code Generation](https://mlsanity.com/paper/2308.02828/) (2023)
- [Theory of Mind for Multi-Agent Collaboration via Large Language Models](https://mlsanity.com/paper/2310.10701/) (2023)
- [Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG](https://mlsanity.com/paper/2410.05983/) (2024)
- [SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2212.07489/) (2022)

## Built on by (most cited first, 26 of 26)

- [Group size effects and collective misalignment in LLM multi-agent systems](https://mlsanity.com/paper/2510.22422/) (2025)
- [Dual Latent Memory for Visual Multi-agent System](https://mlsanity.com/paper/2602.00471/) (2026)
- [Generative AI collective behavior needs an interactionist paradigm](https://mlsanity.com/paper/2601.10567/) (2026)
- [AI Organizations are More Effective but Less Aligned than Individual Agents](https://mlsanity.com/paper/2604.10290/) (2026)
- [Social Theory Should Be a Structural Prior for Agentic AI: A Formal Framework for Multi-Agent Social Systems](https://mlsanity.com/paper/2605.07069/) (2026)
- [MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs](https://mlsanity.com/paper/2605.29512/) (2026)
- [When Parallelism Pays Off: Cohesion-Aware Task Partitioning for Multi-Agent Coding](https://mlsanity.com/paper/2606.00953/) (2026)
- [Parallelism Meets Adaptiveness: Scalable Documents Understanding in Multi-Agent LLM Systems](https://mlsanity.com/paper/2507.17061/) (2025)
- [How large language models judge and influence human cooperation](https://mlsanity.com/paper/2507.00088/) (2025)
- [When Do Multi-Agent Systems Outperform? Analysing the Learning Efficiency of Agentic Systems](https://mlsanity.com/paper/2602.08272/) (2026)
- [Do Agent Societies Develop Intellectual Elites? The Hidden Power Laws of Collective Cognition in LLM Multi-Agent Systems](https://mlsanity.com/paper/2604.02674/) (2026)
- [The Hunger Game Debate: On the Emergence of Over-Competition in Multi-Agent Systems](https://mlsanity.com/paper/2509.26126/) (2025)
- [Towards Ethical Multi-Agent Systems of Large Language Models: A Mechanistic Interpretability Perspective](https://mlsanity.com/paper/2512.04691/) (2025)
- [Discoverable Agent Knowledge -- A Formal Framework for Agentic KG Affordances (Extended Version)](https://mlsanity.com/paper/2605.19186/) (2026)
- [MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination](https://mlsanity.com/paper/2605.22949/) (2026)
- [Competitive Market Behavior of LLMs](https://mlsanity.com/paper/2609.02580/) (2026)
- [Single-Agent Scaling Fails Multi-Agent Intelligence: Towards Foundation Models with Native Multi-Agent Intelligence](https://mlsanity.com/paper/2512.08743/) (2025)
- [Towards a Science of Collective AI: LLM-based Multi-Agent Systems Need a Transition from Blind Trial-and-Error to Rigorous Science](https://mlsanity.com/paper/2602.05289/) (2026)
- [Artificial Organisations](https://mlsanity.com/paper/2602.13275/) (2026)
- [Agentic Social Affordance Framework (ASAF): Agent Identity Design as a Collaboration Interface in Multi-Agent Systems](https://mlsanity.com/paper/2606.09832/) (2026)
- [AgentRadio: Passive Awareness for Long-Horizon Multi-Agent Collaboration](https://mlsanity.com/paper/2607.28430/) (2026)
- [How a shared state is described determines whether AI agents synchronize](https://mlsanity.com/paper/2608.06968/) (2026)
- [An Investigation of the NeurIPS and ICML 2025 Position Tracks](https://mlsanity.com/paper/2608.16894/) (2026)
- [Epistemic-Probabilistic Model for Guarded Multi-Agent LLM Coordination](https://mlsanity.com/paper/2609.29366/) (2026)
- [LLMs for Executable Multi-Agent System Specification Generation](https://mlsanity.com/paper/2609.34619/) (2026)
- [A Society of Researchers: Designing Institutions for Populations of Autonomous Research Agents](https://mlsanity.com/paper/2610.10468/) (2026)

## 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.