@inproceedings{shan-etal-2026-learning,
    title = "Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards",
    author = "Shan, Yingyu  and
      Guo, Yuhang  and
      Cheng, Zihao  and
      Liu, Zeming  and
      Zhu, Xiangrong  and
      Wang, Xinyi  and
      Yao, Jiashu  and
      Lin, Wei  and
      Wang, Hongru  and
      Huang, Heyan",
    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.1766/",
    pages = "37784--37803",
    ISBN = "979-8-89176-462-0"
}