@inproceedings{huang-etal-2026-low,
    title = "Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward",
    author = "Huang, Guanhua  and
      Xu, Tingqiang  and
      Wang, Mingze  and
      Yi, Qi  and
      Gong, Xue  and
      Li, Siheng  and
      Xiong, Ruibin  and
      Li, Kejiao  and
      Jiang, Yuhao  and
      Zhou, Bo",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1209/",
    pages = "24158--24188",
    ISBN = "979-8-89176-395-1"
}