@inproceedings{ren-etal-2026-adora,
    title = "{ADORA}: Training Reasoning Models with Dynamic Advantage Estimation on Reinforcement Learning",
    author = "Ren, Qingnan  and
      Huang, Shiting  and
      Fang, Zhen  and
      Chen, Zehui  and
      Chen, Lin  and
      Li, Lijun  and
      Zhao, Feng",
    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.1258/",
    pages = "28660--28677",
    ISBN = "979-8-89176-459-0"
}