@inproceedings{chan-etal-2025-boosting,
    title = "Boosting Policy and Process Reward Models with {M}onte {C}arlo Tree Search in Open-Domain {QA}",
    author = "Chan, Chi-Min  and
      Xu, Chunpu  and
      Zhu, Junqi  and
      Ji, Jiaming  and
      Hong, Donghai  and
      Wen, Pengcheng  and
      Jiang, Chunyang  and
      Ye, Zhen  and
      Yang, Yaodong  and
      Xue, Wei  and
      Han, Sirui  and
      Guo, Yike",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.findings-acl.388/",
    pages = "7433--7451",
    ISBN = "979-8-89176-256-5"
}