@inproceedings{dou-etal-2025-simulatorarena, title = "{S}imulator{A}rena: Are User Simulators Reliable Proxies for Multi-Turn Evaluation of {AI} Assistants?", author = "Dou, Yao and Galley, Michel and Peng, Baolin and Kedzie, Chris and Cai, Weixin and Ritter, Alan and Quirk, Chris and Xu, Wei and Gao, Jianfeng", editor = "Christodoulopoulos, Christos and Chakraborty, Tanmoy and Rose, Carolyn and Peng, Violet", booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing", month = nov, year = "2025", address = "Suzhou, China", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2025.emnlp-main.1786/", pages = "35200--35278", ISBN = "979-8-89176-332-6" }