@inproceedings{lin-etal-2026-dwdpo,
    title = "dw{DPO}: Training Multi-Turn {LLM} Agents via Divergence-Weighted Direct Preference Optimization",
    author = "Lin, Jinghao  and
      Wu, Yuhang  and
      Wang, Yuanqing  and
      Li, Yuchen  and
      Kang, Tianxingjian  and
      Coskunuzer, Baris  and
      Zheng, Xiawu",
    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.2406/",
    pages = "54657--54674",
    ISBN = "979-8-89176-459-0"
}