@inproceedings{koh-etal-2024-visualwebarena,
    title = "{V}isual{W}eb{A}rena: Evaluating Multimodal Agents on Realistic Visual Web Tasks",
    author = "Koh, Jing Yu  and
      Lo, Robert  and
      Jang, Lawrence  and
      Duvvur, Vikram  and
      Lim, Ming  and
      Huang, Po-Yu  and
      Neubig, Graham  and
      Zhou, Shuyan  and
      Salakhutdinov, Russ  and
      Fried, Daniel",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.acl-long.50/",
    doi = "10.18653/v1/2024.acl-long.50",
    pages = "881--905"
}