# LLM Multi-Agent Systems: Challenges and Open Problems

arXiv: https://arxiv.org/abs/2402.03578 · HTML: https://mlsanity.com/paper/2402.03578/

## Key facts

- Cited by 120 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 28 of its 43 references that are in the map.
- First posted on arXiv 5 Feb 2024.

## 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, 28 of 28)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [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)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://mlsanity.com/paper/2211.12588/) (2022)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [Graph of Thoughts: Solving Elaborate Problems with Large Language Models](https://mlsanity.com/paper/2308.09687/) (2023)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents](https://mlsanity.com/paper/2306.03314/) (2023)
- [Large Language Models as Tool Makers](https://mlsanity.com/paper/2305.17126/) (2023)
- [Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security](https://mlsanity.com/paper/2401.05459/) (2024)
- [Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View](https://mlsanity.com/paper/2310.02124/) (2023)
- [Large Language Model Guided Tree-of-Thought](https://mlsanity.com/paper/2305.08291/) (2023)
- [Augmenting Language Models with Long-Term Memory](https://mlsanity.com/paper/2306.07174/) (2023)
- [Rationale-Augmented Ensembles in Language Models](https://mlsanity.com/paper/2207.00747/) (2022)
- [Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems?](https://mlsanity.com/paper/2309.15943/) (2023)
- [Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents](https://mlsanity.com/paper/2311.11797/) (2023)
- [Tab-CoT: Zero-shot Tabular Chain of Thought](https://mlsanity.com/paper/2305.17812/) (2023)
- [CGMI: Configurable General Multi-Agent Interaction Framework](https://mlsanity.com/paper/2308.12503/) (2023)
- [MoT: Memory-of-Thought Enables ChatGPT to Self-Improve](https://mlsanity.com/paper/2305.05181/) (2023)
- [Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learning](https://mlsanity.com/paper/1901.08492/) (2019)
- [Prompt-Guided Retrieval Augmentation for Non-Knowledge-Intensive Tasks](https://mlsanity.com/paper/2305.17653/) (2023)
- [Oracles & Followers: Stackelberg Equilibria in Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2210.11942/) (2022)

## Built on by (most cited first, 30 of 120)

- [AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents](https://mlsanity.com/paper/2503.18666/) (2025)
- [Large Language Model-Brained GUI Agents: A Survey](https://mlsanity.com/paper/2411.18279/) (2024)
- [Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2410.02506/) (2024)
- [Determinants of LLM-assisted Decision-Making](https://mlsanity.com/paper/2402.17385/) (2024)
- [Internal Consistency and Self-Feedback in Large Language Models: A Survey](https://mlsanity.com/paper/2407.14507/) (2024)
- [SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning](https://mlsanity.com/paper/2502.04780/) (2025)
- [A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents](https://mlsanity.com/paper/2602.06052/) (2026)
- [UFO2: The Desktop AgentOS](https://mlsanity.com/paper/2504.14603/) (2025)
- [PathFinder: A Multi-Modal Multi-Agent System for Medical Diagnostic Decision-Making Applied to Histopathology](https://mlsanity.com/paper/2502.08916/) (2025)
- [Who is Introducing the Failure? Automatically Attributing Failures of Multi-Agent Systems via Spectrum Analysis](https://mlsanity.com/paper/2509.13782/) (2025)
- [From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users](https://mlsanity.com/paper/2508.17281/) (2025)
- [ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks](https://mlsanity.com/paper/2503.02390/) (2025)
- [Shifting AI Efficiency From Model-Centric to Data-Centric Compression](https://mlsanity.com/paper/2505.19147/) (2025)
- [From Sora What We Can See: A Survey of Text-to-Video Generation](https://mlsanity.com/paper/2405.10674/) (2024)
- [Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence](https://mlsanity.com/paper/2410.11163/) (2024)
- [Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities](https://mlsanity.com/paper/2506.18019/) (2025)
- [Reinforcement Learning from Multi-role Debates as Feedback for Bias Mitigation in LLMs](https://mlsanity.com/paper/2404.10160/) (2024)
- [Large Language Model Reasoning Failures](https://mlsanity.com/paper/2602.06176/) (2026)
- [BattleAgent: Multi-modal Dynamic Emulation on Historical Battles to Complement Historical Analysis](https://mlsanity.com/paper/2404.15532/) (2024)
- [Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance Graphs](https://mlsanity.com/paper/2601.11369/) (2026)
- [Towards Effective GenAI Multi-Agent Collaboration: Design and Evaluation for Enterprise Applications](https://mlsanity.com/paper/2412.05449/) (2024)
- [Agent-X: Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Tasks](https://mlsanity.com/paper/2505.24876/) (2025)
- [Securing GenAI Multi-Agent Systems Against Tool Squatting: A Zero Trust Registry-Based Approach](https://mlsanity.com/paper/2504.19951/) (2025)
- [Talk Structurally, Act Hierarchically: A Collaborative Framework for LLM Multi-Agent Systems](https://mlsanity.com/paper/2502.11098/) (2025)
- [P2P: Automated Paper-to-Poster Generation and Fine-Grained Benchmark](https://mlsanity.com/paper/2505.17104/) (2025)
- [MorphAgent: Empowering Agents through Self-Evolving Profiles and Decentralized Collaboration](https://mlsanity.com/paper/2410.15048/) (2024)
- [Self-Resource Allocation in Multi-Agent LLM Systems](https://mlsanity.com/paper/2504.02051/) (2025)
- [LLM DNA: Tracing Model Evolution via Functional Representations](https://mlsanity.com/paper/2509.24496/) (2025)
- [ParallelMuse: Agentic Parallel Thinking for Deep Information Seeking](https://mlsanity.com/paper/2510.24698/) (2025)
- [CoLMDriver: LLM-based Negotiation Benefits Cooperative Autonomous Driving](https://mlsanity.com/paper/2503.08683/) (2025)

## 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.