@inproceedings{koh24acl,
    title = {VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks},
    author = {Jing Yu Koh and Robert Lo and Lawrence Jang and Vikram Duvvur and Ming Chong Lim and Po-Yu Huang and Graham Neubig and Shuyan Zhou and Ruslan Salakhutdinov and Daniel Fried},
    booktitle = {Annual Conference of the Association for Computational Linguistics (ACL)},
    address = {Bangkok, Thailand},
    month = {August},
    url = {https://arxiv.org/abs/2401.13649},
    year = {2024}
}