@inproceedings{wan-etal-2026-agents, title = "Can Agents Read the Room? Benchmarking Visual Social Intelligence in Multimodal Simulation", author = "Wan, Shijun and Wu, Xuehai and Zhang, Jiwen and Wang, Siyuan and Wei, Zhongyu", editor = "Lee, Hung-Yi and Dev, Sunipa and Li, Jessy and Elliott, Desmond", booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026", month = oct, year = "2026", address = "Budapest, Hungary", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2026.findings-emnlp.956/", pages = "20179--20209", ISBN = "979-8-89176-462-0" }