@inproceedings{tan-etal-2026-bottom,
    title = "Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies",
    author = "Tan, Yuqiao  and
      Wang, Minzheng  and
      He, Shizhu  and
      Liao, Huanxuan  and
      Zhao, Chengfeng  and
      Liang, Tian  and
      Zhao, Jun  and
      Liu, Kang",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.1173/",
    pages = "26891--26910",
    ISBN = "979-8-89176-459-0"
}