@inproceedings{zhu-etal-2026-gagpo,
    title = "{GAGPO}: Generalized Advantage Grouped Policy Optimization",
    author = "Zhu, Siyuan  and
      Yu, Chao  and
      Yang, Rongxin  and
      Liu, Zongkai  and
      Hu, Jinjun  and
      Chen, Qiwen  and
      Zhang, Yibo",
    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.864/",
    pages = "18261--18274",
    ISBN = "979-8-89176-462-0"
}