Zeng, Hui, Daming Zhao, Pengfei Yang, WenXuan Hou, Tianyang Zheng, Hui Li, Weiye Ji, and Jidong Zhai. “Lethe: Layer- and Time-Adaptive KV Cache Pruning for Reasoning-Intensive LLM Serving”. Proceedings of the AAAI Conference on Artificial Intelligence 40, no. 33 (March 14, 2026): 28103–28112. Accessed May 14, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/40036.