@inproceedings{sun-etal-2026-mmedagentbench,
    title = "{MM}ed{A}gent{B}ench: A Multi-Stage Benchmark for Evaluating {LLM}-based Medical Agents",
    author = "Sun, Lu  and
      Zhang, Xiangyi  and
      Zhu, Xiangyang  and
      Ji, Kaiyuan  and
      Chen, Zijian  and
      Hu, Qiang  and
      Zhang, Zicheng  and
      Tian, Yuan  and
      Zhai, Guangtao",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.469/",
    pages = "10780--10793",
    ISBN = "979-8-89176-459-0"
}