@inproceedings{yu-etal-2026-reinforcement,
    title = "Reinforcement Learning with Robust Rubric Rewards",
    author = "Yu, Ya-Qi  and
      Wang, Hao  and
      Hong, Fangyu  and
      Qu, Xiangyang  and
      Wu, Gaojie  and
      Luo, Qiaoyu  and
      Xu, Nuo  and
      Wang, Huixin  and
      Xu, Wuheng  and
      Liao, Yongxin  and
      Chen, Zihao  and
      Li, Haonan  and
      Li, Ziming  and
      Peng, Dezhi  and
      Liao, Minghui  and
      Wu, Jihao  and
      Ren, Haoyu  and
      Tu, Dandan",
    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.2554/",
    pages = "58060--58078",
    ISBN = "979-8-89176-459-0"
}