@inproceedings{zheng-etal-2026-reward,
    title = "When Reward-Free Signals Are Not Directions: A Gradient-Level Diagnostic for Test-Time Reasoning Optimization",
    author = "Zheng, Shijie  and
      Dai, Yinxing  and
      Pu, Zhiqiang",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-emnlp.1166/",
    doi = "10.18653/2026.findings-emnlp.1166",
    pages = "24687--24703",
    ISBN = "979-8-89176-462-0"
}