@inproceedings{bodhwani-etal-2026-gauge,
    title = "{GAUGE}: When Not to Trust {LLM}-as-a-Judge in User-Simulated Evaluation of Task-Oriented Agents",
    author = "Bodhwani, Umesh  and
      Tran, Thanh  and
      Wei, Kai",
    editor = "Atanasova, Pepa  and
      Haffari, Gholamreza  and
      Wang, Minghan",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-industry.190/",
    pages = "3197--3216",
    ISBN = "979-8-89176-460-6"
}