@inproceedings{gan-etal-2026-thinking,
    title = "Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning",
    author = "Gan, Siyuan  and
      Liu, Jiaheng  and
      Wang, Boyan  and
      Yang, Tianpei  and
      Miao, Runqing  and
      Zhang, Yuyao  and
      Meng, Fanyu  and
      Feng, Junlan  and
      Meng, Linjian  and
      Huo, Jing  and
      Gao, Yang",
    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.2122/",
    pages = "45754--45771",
    ISBN = "979-8-89176-390-6"
}