@inproceedings{chen-etal-2026-efficient-multimodal,
    title = "Efficient Multimodal Planning Agent for Visual Question-Answering",
    author = "Chen, Zhuo  and
      Geng, Xinyu  and
      Wang, Xinyu  and
      Jiang, Yong  and
      Zhang, Zhen  and
      Xie, Pengjun  and
      Tu, Kewei",
    editor = "Zhang, Yue  and
      Xu, Ruifeng  and
      Purwarianti, Ayu  and
      Rong, Tong  and
      Suzuki, Jun",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
    month = nov,
    year = "2026",
    address = "Hengqin, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-aacl.239/",
    pages = "4698--4718",
    ISBN = "979-8-89176-444-6"
}