@inproceedings{wang-etal-2025-offline,
    title = "Offline Reinforcement Learning for {LLM} Multi-step Reasoning",
    author = "Wang, Huaijie  and
      Hao, Shibo  and
      Dong, Hanze  and
      Zhang, Shenao  and
      Bao, Yilin  and
      Yang, Ziran  and
      Wu, Yi",
    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/display_plenaries/2025.findings-acl.464/",
    pages = "8881--8893",
    ISBN = "979-8-89176-256-5"
}