@inproceedings{ge-etal-2026-vtos,
    title = "{VTOS}: Learning to Orchestrate Vision Tools by Co-Searching Solutions and Observers",
    author = "Ge, Jinchao  and
      Liu, Lingqiao  and
      Zhao, Shuwen  and
      Wang, Lei",
    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.977/",
    pages = "22551--22569",
    ISBN = "979-8-89176-459-0"
}