@inproceedings{khalifa-etal-2026-gaming,
    title = "Gaming the Judge: How Unfaithful Chain-of-Thought Can Undermine Agent Evaluation",
    author = "Khalifa, Muhammad  and
      Logeswaran, Lajanugen  and
      Kim, Jaekyeom  and
      Sohn, Sungryull  and
      Zhang, Yunxiang  and
      Lee, Moontae  and
      Peng, Hao  and
      Wang, Lu  and
      Lee, Honglak",
    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.1636/",
    pages = "34789--34825",
    ISBN = "979-8-89176-462-0"
}