AgentKV: Phase-Aware KV Eviction for Agentic LLMs
This work proposes AGENTKV, which maintains a small query buffer per phase and scores cached keys against their union and implements AGENTKV in a persistent multi-turn serving path that carries compressed KV state across turns and compacts retained KV pages online.
T. Liu, Jeffrey T. H. Wong, Can Xiao et al.
· 1 citation