@inproceedings{su-etal-2026-longflow, title = "{L}ong{F}low: Efficient {KV} Cache Compression for Reasoning Models", author = "Su, Yi and Tian, Zhenxu and Qiao, Dan and Zhou, Yuechi and Yang, Zheming and Li, Juntao and Zhang, Min", editor = "Lee, Hung-Yi and Dev, Sunipa and Li, Jessy and Elliott, Desmond", booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing", month = oct, year = "2026", address = "Budapest, Hungary", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2026.emnlp-main.112/", pages = "2629--2645", ISBN = "979-8-89176-459-0" }