@inproceedings{wang-etal-2025-agentdropout,
    title = "{A}gent{D}ropout: Dynamic Agent Elimination for Token-Efficient and High-Performance {LLM}-Based Multi-Agent Collaboration",
    author = "Wang, Zhexuan  and
      Wang, Yutong  and
      Liu, Xuebo  and
      Ding, Liang  and
      Zhang, Miao  and
      Liu, Jie  and
      Zhang, Min",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.1170/",
    pages = "24013--24035",
    ISBN = "979-8-89176-251-0",
    abstract = "Multi-agent systems (MAS) based on large language models (LLMs) have demonstrated significant potential in collaborative problem-solving. However, they still face substantial challenges of low communication efficiency and suboptimal task performance, making the careful design of the agents' communication topologies particularly important. Inspired by the management theory that roles in an efficient team are often dynamically adjusted, we propose $\textbf{AgentDropout}$, which identifies redundant agents and communication across different communication rounds by optimizing the adjacency matrices of the communication graphs and eliminates them to enhance both token efficiency and task performance. Compared to state-of-the-art methods, AgentDropout achieves an average reduction of 21.6{\%} in prompt token consumption and 18.4{\%} in completion token consumption, along with a performance improvement of 1.14 on the tasks. Furthermore, the extended experiments demonstrate that AgentDropout achieves notable domain transferability and structure robustness, revealing its reliability and effectiveness. We release our code at https://github.com/wangzx1219/AgentDropout."
}