SOURCE-LINKED INTELLIGENCE

KVShareArena: KV-Cache Reuse Across Contexts and Model Checkpoints

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

LLM serving systems already reuse KV caches, but only when the reused text sits at the very start of the prompt. Two growing workloads break this condition: a retrieval-augmented generation server assembles a different set of retrieved chunks for every query, and a multi-agent coordinator reads reports written by other agents. Reused inside a new prompt, a cache carries the wrong positions and never attended to the other sources. The cache may also have been written by a different checkpoint of the same model family, which changes the stored values. Repair methods for such caches have appeared

Read original source ↗ Open in workspace

recordType

paper

region

Global