@inproceedings{gao-etal-2025-towards,
    title = "Towards A Better Initial Policy Model For Scalable Long-{C}o{T} Reinforcement Learning",
    author = "Gao, Bofei  and
      Wang, Yejie  and
      Miao, Yibo  and
      Wu, Ruoyu  and
      Song, Feifan  and
      Yu, Longhui  and
      Liu, Tianyu  and
      Chang, Baobao",
    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.397/",
    pages = "7652--7665",
    ISBN = "979-8-89176-256-5"
}