@inproceedings{yss-etal-2026-gradient,
    title = "A Gradient Perspective on {RLVR} Stability and Winner-Advantage Policy Optimization",
    author = "Yss, Prasanth  and
      Ren, Zhichen  and
      Hosseinzadeh, Rasa  and
      Gofman, Ilan  and
      Chen, Yuqi  and
      Liu, Zhaoyan  and
      Yu, Guangwei  and
      Cresswell, Jesse C.  and
      Gorti, Satya Krishna",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.2371/",
    pages = "53806--53826",
    ISBN = "979-8-89176-459-0"
}