@inproceedings{huang-etal-2026-rewardcode,
    title = "{R}eward{C}ode: Training Generalist Code Reward Model via Pairwise Reinforcement Learning",
    author = "Huang, Songtao  and
      Feng, Shiyang  and
      He, Xiaohan  and
      Yan, Xiangchao  and
      Zhang, Bo  and
      Bai, Lei",
    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.448/",
    pages = "9409--9431",
    ISBN = "979-8-89176-462-0"
}