@inproceedings{shi-etal-2025-mutual,
    title = "Mutual-Taught for Co-adapting Policy and Reward Models",
    author = "Shi, Tianyuan  and
      Huang, Canbin  and
      Wan, Fanqi  and
      Zhong, Longguang  and
      Yang, Ziyi  and
      Shen, Weizhou  and
      Quan, Xiaojun  and
      Yan, Ming",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.acl-long.794/",
    pages = "16285--16298",
    ISBN = "979-8-89176-251-0"
}