@inproceedings{chen-etal-2026-rethinking-rl,
    title = "Rethinking {RL} Evaluation: Can Benchmarks Truly Reveal Failures of {RL} Methods?",
    author = "Chen, Zihan  and
      Zhang, Yiming  and
      Zhou, Hengguang  and
      Ding, Zenghui  and
      Sun, Yining  and
      Hsieh, Cho-Jui",
    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.769/",
    pages = "15692--15709",
    ISBN = "979-8-89176-395-1"
}