@inproceedings{lin-etal-2026-mm,
    title = "{MM}-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning",
    author = "Lin, Jiahang  and
      Hu, Kai  and
      Wang, Binghai  and
      Zhou, Yuhao  and
      Xi, Zhiheng  and
      Guo, Honglin  and
      Liu, Shichun  and
      Wang, Junzhe  and
      Dou, Shihan  and
      Zhou, Enyu  and
      Yan, Hang  and
      Han, Zhenhua  and
      Gui, Tao  and
      Zhang, Qi  and
      Huang, Xuanjing",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1488/",
    pages = "29770--29783",
    ISBN = "979-8-89176-395-1"
}