Zeng, Hui, Daming Zhao, Pengfei Yang, WenXuan Hou, Tianyang Zheng, Hui Li, Weiye Ji, and Jidong Zhai. 2026. “Lethe: Layer- and Time-Adaptive KV Cache Pruning for Reasoning-Intensive LLM Serving”. Proceedings of the AAAI Conference on Artificial Intelligence 40 (33):28103-12. https://doi.org/10.1609/aaai.v40i33.40036.