@inproceedings{ye-etal-2026-listening,
    title = "Listening to the Echo: User-Reaction Aware Policy Optimization via Scalar-Verbal Hybrid Reinforcement Learning",
    author = "Ye, Jing  and
      Zhao, Xinpei  and
      Xiang, Lu  and
      Zhang, Yaping  and
      Zong, Chengqing",
    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.73/",
    pages = "1485--1515",
    ISBN = "979-8-89176-462-0"
}