@inproceedings{liu-etal-2026-teacher,
    title = "Teacher-Guided Policy Optimization for On-Policy Reasoning Distillation under Large Policy Divergence",
    author = "Liu, Xinyu  and
      Jiao, Kechen  and
      Xiao, Chunyang  and
      Zhao, Runsong  and
      Ruan, Junhao  and
      Li, Bei  and
      Liu, Jiahao  and
      Wang, Qifan  and
      Chen, Xin  and
      Wang, Jingang  and
      Wang, Chenglong  and
      Xiao, Tong  and
      Zhu, JingBo",
    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.1172/",
    pages = "24801--24816",
    ISBN = "979-8-89176-462-0"
}