@inproceedings{liu-etal-2026-gd2po,
    title = "{GD}$^2${PO}: Group-Dynamic Reward-Decoupled Policy Optimization for Mitigating Multi-Reward {RL} Conflicts",
    author = "Liu, Haotian  and
      Liu, Yihao  and
      Ni, Jingwei  and
      Huang, Siyuan  and
      Liu, Xinpeng  and
      Cheng, Pengyu  and
      Song, Jiajun  and
      Ding, Ruijin  and
      Li, Junfeng  and
      Yu, Zhechao  and
      Zhou, Mengyu  and
      Xu, Hongteng  and
      Jiang, Xiaoxi  and
      Jiang, Guanjun",
    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.1070/",
    pages = "22624--22644",
    ISBN = "979-8-89176-462-0"
}