@inproceedings{chen-etal-2026-agentslimming,
    title = "{A}gent{S}limming: Towards Efficient and Cost-Aware Multi-Agent Systems",
    author = "Chen, Yulang  and
      Peng, Haoxuan  and
      Liu, Jinyan  and
      Wen, Zichen  and
      Liu, Dongrui  and
      Zhang, Linfeng",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1387/",
    pages = "30064--30086",
    ISBN = "979-8-89176-390-6",
    abstract = "Large Language Model-based Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in complex tasks. However, manually designing optimal communication topologies is labor-intensive, while automated expansion methods often result in bloated structures with redundant agents, leading to excessive token consumption. To address this problem, we introduce AgentSlimming, a plug-and-play compression framework for graph-structured multi-agent workflows. Motivated by the AgentPruner and AgentQuant in neural networks, AgentSlimming compresses workflows by firstly estimate the importance score of each agent with a hybrid mechanism, and then removing redundant agents or replacing them with low-cost ones, where each operation is then validated with a baseline-anchored acceptance rule to prevent performance collapse. Experiments show that AgentSlimming reduces average token cost by up to 78.9{\%} with negligible performance degradation, and even sometimes improves accuracy, achieving a strong Pareto-optimal trade-off between cost and quality."
}