@inproceedings{zhang-etal-2025-turnbench, title = "{T}urn{B}ench-{MS}: A Benchmark for Evaluating Multi-Turn, Multi-Step Reasoning in Large Language Models", author = "Zhang, Yiran and Wang, Mo and Li, Xiaoyang and Ren, Kaixuan and Zhu, Chencheng and Naseem, Usman", editor = "Christodoulopoulos, Christos and Chakraborty, Tanmoy and Rose, Carolyn and Peng, Violet", booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025", month = nov, year = "2025", address = "Suzhou, China", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.1084/", doi = "10.18653/v1/2025.findings-emnlp.1084", pages = "19892--19924", ISBN = "979-8-89176-335-7" }