PaperNote 3 [Note] BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference Sep 4, 2026 [Note] EvoRoute: Experience-Driven Self-Routing LLM Agent Systems Apr 20, 2026 [Note] FreeKV: Boosting KV Cache Retrieval For Efficient LLM Inference Mar 16, 2026