@inproceedings{sun-etal-2026-topodim,
    title = "{T}opo{DIM}: One-shot Topology Generation of Diverse Interaction Modes for Multi-Agent Systems",
    author = "Sun, Rui  and
      Ding, Jie  and
      Gong, Chenghua  and
      Gu, Tianjun  and
      Jiang, Yihang  and
      Zhang, Juyuan  and
      Pan, Liming  and
      L{\textbackslash}{''}u, Linyuan",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.207/",
    pages = "4252--4269",
    ISBN = "979-8-89176-395-1",
    abstract = "Optimizing communication topology in LLM{--}based multi-agent system is critical for enabling collective intelligence. Existing methods mainly rely on spatio-temporal interaction paradigms, where the sequential execution of multi-round dialogues incurs high latency and computation. Motivated by the recent insights that evaluation and debate mechanisms can improve problem-solving in multi-agent systems, we propose TopoDIM, a framework for one-shot Topology generation with Diverse Interaction Modes. Designed for decentralized execution to enhance adaptability and privacy, TopoDIM enables agents to autonomously construct heterogeneous communication without iterative coordination, achieving token efficiency and improved task performance. Experiments demonstrate that TopoDIM reduces total token consumption by 46.41{\%} while improving average performance by 1.50{\%} over state-of-the-art methods. Moreover, the framework exhibits strong adaptability in organizing communication among heterogeneous agents. Code is available at: https://github.com/Sundiasy/TopoDIM."
}