LLM Multi-Agent Systems: Challenges and Open Problems

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.

@article{han2025_2402.03578,
  title={ LLM Multi-Agent Systems: Challenges and Open Problems },
  author={ Shanshan Han and Qifan Zhang and Yuhang Yao and Weizhao Jin and Zhaozhuo Xu },
  journal={arXiv preprint arXiv:2402.03578},
  year={ 2025 }
}