@inproceedings{tang-zheng-2026-measuring,
    title = "Measuring the Serving Stack Instead of the Model: Hidden Confounds in Local Tool-Use Evaluation",
    author = "Tang, Lijuan  and
      Zheng, Yuemeng",
    editor = "Kamalloo, Ehsan  and
      Gontier, Nicolas  and
      Rozanov, Nikolai  and
      Hashemzadeh, Maryam  and
      Arora, Akhil",
    booktitle = "Proceedings of the Second Workshop for {RE}search on Agent Language Models ({REALM} 2026)",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.realm-1.7/",
    pages = "86--94",
    ISBN = "979-8-89176-485-9"
}