RestoreKV: Recovering Full-Cache Behavior Under Aggressive Query-Agnostic KV Cache Eviction

• 类型：arxiv
• 标识：2608.01247
• 链接：https://arxiv.org/abs/2608.01247
• 主分类：llm-infra
• 形态：method
• 被引：0
• 被引来源：Semantic Scholar
• S2被引：0
• 影响力被引：0
• TLDR：RestoreKV is introduced, which complements this selection-based formulation with learned restoration with learned restoration under the same total KV budget, and substantially reduces compression-induced degradation.
• 待LLM分类：否
• 标题中文：RestoreKV: 在激进 Query-Agnostic KV Cache 淘汰下恢复全缓存行为
• TLDR中文：提出 RestoreKV，在相同 KV 总预算下以可学习的恢复机制补充基于选择的 KV 压缩方案，显著降低压缩带来的性能损失。
• 来源文件：
• /inbox/tom/_candidates/2026-08-06-agent-rag-longcontext-candidates.json
• [S2 enrich]