@inproceedings{yang-etal-2026-internalize,
    title = "Internalize the Temperature: On-Policy Self-Distillation as Policy Reheater for Reinforcement Learning",
    author = "Yang, Xuewei  and
      Yu, Jiachen  and
      Wu, Jie  and
      Sun, Shaoning  and
      Wang, Junjie  and
      Yang, Yujiu",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-emnlp.1727/",
    pages = "36939--36956",
    ISBN = "979-8-89176-462-0"
}