Preprint
Nov 2026
EchoKV: Self-Corrective KV Cache Eviction via Iterative Query Feedback
KV cache eviction is not merely a token-ranking problem: the workspace retained for generating eviction queries also determines the quality of those queries. Consequently, an early workspace error can distort later query observations and reinforce an incorrect final eviction decision, particularly when evidence is disp...
Jian-Kun Zou, Tong-Tong Yuan
· 0 citations