@inproceedings{tan-etal-2026-scaling,
    title = "Scaling Behaviors of {LLM} Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning",
    author = "Tan, Zelin  and
      Geng, Hejia  and
      Yu, Xiaohang  and
      Zhang, Mulei  and
      Wan, Guancheng  and
      Zhou, Yifan  and
      He, Qiang  and
      Xue, Xiangyuan  and
      Zhou, Heng  and
      Fan, Yutao  and
      Li, Zhong-Zhi  and
      Zhang, Zaibin  and
      Zhang, Guibin  and
      Zhang, Chen  and
      Yin, Zhenfei  and
      Torr, Philip  and
      Bai, Lei",
    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.1444/",
    pages = "31300--31319",
    ISBN = "979-8-89176-390-6"
}