@inproceedings{zhang-etal-2026-evohyper,
    title = "{E}vo{H}yper: Evolving Hypergraph Topologies for Unified Collaboration in Multi-Agent Communication",
    author = "Zhang, Heng  and
      Zhong, Yihao  and
      Gan, Lubin  and
      Chen, Zhihe  and
      Wu, Jiajun  and
      Shi, Yuling  and
      Gu, Xiaodong  and
      Zhang, Hao  and
      You, Haochen  and
      Huang, Jin",
    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.1258/",
    pages = "25130--25143",
    ISBN = "979-8-89176-395-1",
    abstract = "Multi-agent systems powered by large language models have achieved strong performance on complex tasks, yet naive collaboration topologies often cause high communication costs and redundant context. Existing methods usually use a fixed communication graph and manage collaboration structure and shared memory in separate modules. Our log analysis of several representative systems shows that this separation leads to multiple copies of the same key facts in dialogue, memory and model inputs. We address this issue with EvoHyper, a framework based on an evolving hypergraph topology for multi-agent collaboration. In EvoHyper, a single hypergraph represents agents and shared memory, and each hyperedge serves as a collaboration unit that binds a group of agents to that shared memory. During execution a controller edits the hypergraph through a small set of predefined evolution operations, so collaboration units can spawn, update and merge as tasks unfold. Experiments on four benchmarks covering mathematical reasoning and code generation show that EvoHyper is (I) high-performing, achieving 3.2{\%} to 7.8{\%} accuracy gains over state-of-the-art methods, (II) efficient, reducing token consumption by up to 23.5{\%}, and (III) adaptive, adjusting topology complexity according to task requirements."
}