@inproceedings{yao-etal-2026-ace,
    title = "{ACE}-Router: Generalizing History-Aware Routing from {MCP} Tools to the Agent Web",
    author = "Yao, Zhiyuan  and
      Xu, Zishan  and
      Guo, Yifu  and
      Han, Zhiguang  and
      Yang, Cheng  and
      Zhang, Shuo  and
      Zhang, Weinan  and
      Zeng, Xingshan  and
      Liu, Weiwen",
    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.281/",
    pages = "6224--6240",
    ISBN = "979-8-89176-390-6",
    abstract = "With the rise of the Agent Web and Model Context Protocol (MCP), the agent ecosystem is evolving into an open collaborative network, exponentially increasing accessible tools. However, current architectures face severe scalability and generality bottlenecks. To address this, we propose ACE-Router, a pipeline for training history-aware routers to empower precise navigation in large-scale ecosystems. By leveraging a dependency-rich candidate Graph to synthesize multi-turn trajectories, we effectively train routers with dynamic context understanding to create the plug-and-play Light Routing Agent. Experiments on the real-world benchmarks MCP-Universe and MCP-Mark demonstrate superior performance. Notably, ACE-Router exhibits critical properties for the future Agent Web: it not only generalizes to multi-agent collaboration with minimal adaptation but also maintains exceptional robustness against noise and scales effectively to massive candidate spaces. These findings provide a strong empirical foundation for universal orchestration in open-ended ecosystems.Our code is available at https://github.com/euyis1019/ACE-Router."
}