@inproceedings{liu-etal-2025-epo,
    title = "{EPO}: Explicit Policy Optimization for Strategic Reasoning in {LLM}s via Reinforcement Learning",
    author = "Liu, Xiaoqian  and
      Wang, Ke  and
      Li, Yongbin  and
      Wu, Yuchuan  and
      Ma, Wentao  and
      Kong, Aobo  and
      Huang, Fei  and
      Jiao, Jianbin  and
      Zhang, Junge",
    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.747/",
    pages = "15371--15396",
    ISBN = "979-8-89176-251-0"
}