@inproceedings{ye-etal-2025-toolhop, title = "{T}ool{H}op: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use", author = "Ye, Junjie and Du, Zhengyin and Yao, Xuesong and Lin, Weijian and Xu, Yufei and Chen, Zehui and Wang, Zaiyuan and Zhu, Sining and Xi, Zhiheng and Yuan, Siyu and Gui, Tao and Zhang, Qi and Huang, Xuanjing and Chen, Jiecao", editor = "Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher", booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", month = jul, year = "2025", address = "Vienna, Austria", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/landing_page/2025.acl-long.150/", pages = "2995--3021", ISBN = "979-8-89176-251-0" }