@inproceedings{peng-etal-2026-llm,
    title = "Can {LLM}-as-a-Judge Reliably Verify Rubrics in Agentic Scenarios?",
    author = "Peng, Yangda  and
      Qi, Yunjia  and
      Xia, Haotian  and
      He, Guanzhong  and
      Shi, Xintong  and
      Xuan, Richeng  and
      Lu, Songyuanyi  and
      Liu, Yixian  and
      Hu, Zhichao  and
      Yuhong, Lliu  and
      Peng, Hao",
    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.2192/",
    pages = "49833--49851",
    ISBN = "979-8-89176-459-0"
}