@inproceedings{zhang-etal-2026-stepopsd,
    title = "{S}tep{OPSD}: Step-Aware Online Preference Self-Distillation for Agent Reinforcement Learning",
    author = "Zhang, Yanfei  and
      Lin, Xu  and
      Wu, Chenglin",
    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.209/",
    pages = "4380--4390",
    ISBN = "979-8-89176-462-0"
}