@inproceedings{choi-etal-2026-mentor,
    title = "{MENTOR}: Reinforcement Learning via Flexible Teacher-Optimized Rewards for Tool-Use Distillation",
    author = "Choi, ChangSu  and
      Song, Hoyun  and
      Kim, Dongyeon  and
      Cho, Minkyung  and
      Jung, WooHyeon  and
      Park, SunJin  and
      Bae, NohHyeob  and
      Yu, Seona  and
      Lim, KyungTae",
    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.1286/",
    pages = "29289--29319",
    ISBN = "979-8-89176-459-0"
}