@inproceedings{wu-etal-2026-trac,
    title = "{TRAC}: Teacher-Guided Token Reward with Adaptive Calibration for Robust Policy Optimization",
    author = "Wu, Sitong  and
      Tan, Haoru  and
      Zhang, Xichen  and
      Xia, Bin  and
      Zhang, Wenhu  and
      Qi, Xiaojuan  and
      Yu, Bei  and
      Jia, Jiaya",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.2210/",
    pages = "47869--47884",
    ISBN = "979-8-89176-390-6"
}