arXiv cs.AI· JianKun Zou, Tongtong Yuan·· 12 小时前AI 评分26
EchoKV：通过迭代查询反馈实现自纠正的 KV Cache 驱逐
EchoKV: Self-Corrective KV Cache Eviction via Iterative Query Feedback
AI 导读
EchoKV 提出一种自纠正的 KV cache 驱逐方法，通过迭代查询反馈修复工作区错误，解决查询与工作区耦合导致的驱逐决策偏差。该方法与 LAQ 使用相同数量的工作区前向传播，仅增加一次张量重打分操作。
正文 · 原文
Abstract: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 dispersed across a long context. We present EchoKV, which discovers and addresses this failure mode with iterative correction. It initializes a feedback-compatible bootstrap workspace using proposals at future decode positions, then uses early decode-generated queries to recover the workspace before the remaining lookahead steps. It uses the same number of workspace forward passes as LAQ while adding a tensor re-scoring operation for workspace repair. On LongBench (16 tasks, Mistral-7B-Instruct-v0.2 and Qwen2.5-7B-Instruct), EchoKV shows notable improvements over LAQ on several tasks requiring dispersed evidence, including multi-hop cross-document QA and long single-document comprehension. Across budgets and backbones, EchoKV selectively improves evidence-intensive tasks while maintaining comparable performance on the remaining LongBench subsets. These results identify query--workspace coupling as a practical failure mode of query-driven KV eviction.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.05903 [cs.AI] |
| (or arXiv:2611.05903v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.05903 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jiankun Zou [view email]
[v1]
Wed, 4 Nov 2026 03:52:59 UTC (619 KB)
来源：arXiv cs.AI · arxiv.org