2 papers
cs.AI2026
KV-Rescue: Recovering Reasoning Language Model KV Eviction Loss via Stepwise Interleaving
Minsoo Cheong, Woosang Lim, Vincent-Daniel Yun +1
KV-cache eviction caps the memory cost of long reasoning traces but is inherently lossy because the model decodes from a partial view of its history. Under aggressive budgets, this…
cs.LG2026
GraniKV: Asymmetric Granularity KV-Cache Paging for Multi-Agent Systems with Long Shared Prefix
Jinhyun Jeon, Sungjoo Yoo
Production paged-serving engines apply uniform paging granularity to the KV cache, even though the two regions of a multi-agent workload have opposite storage requirements: a long…