Zeng, H., Zhao, D., Yang, P., Hou, W., Zheng, T., Li, H., … Zhai, J. (2026). Lethe: Layer- and Time-Adaptive KV Cache Pruning for Reasoning-Intensive LLM Serving. Proceedings of the AAAI Conference on Artificial Intelligence, 40(33), 28103–28112. https://doi.org/10.1609/aaai.v40i33.40036