新论文提出智能体 KV 缓存自管理方法，成本再降 7.1%
一篇把智能体省钱做到 KV 缓存层的论文，让智能体自己改缓存策略，比摘要方案省 27.7% 成本，跑长任务的值得看。
该论文把智能体的上下文工程推进到缓存工程层面，聚焦长时间运行智能体的 KV cache 管理。方法给智能体两个操作接口：删除未来注意力中的条目和移动保留 key 的位置，轨迹文本保持不变，从而让智能体自己定义和优化缓存策略。通过递归自我改进缓存策略，比专家设计的方案再降 7.1% 成本。滚动删除旧工具响应比阈值触发摘要高 1.7 分且省 27.7% 成本，AKV serving 引擎吞吐提升至 1.2x、P95 延迟快 1.5x。
We love papers that go deeper down the stack.
This is a good example that shifts from agentic context engineering to agentic cache engineering.
They also apply recursive self-improvement to cache policies to further reduce cost by 7.1% over expert design.
Specifically, this work focuses on KV cache management in long-running agents.
When an agent summarizes or trims its history, the prefix change invalidates the cache after it, and the retained context must be prefilled again.
Cache engineering gives the agent two operations on its own KV cache. One removes entries from future attention, and the other shifts the positions of the keys that remain. The trajectory text stays unchanged. This essentially provides a programmable interface for agents to define and refine their own cache engineering strategies.
A rolling drop of old tool responses scores 1.7 points higher and costs 27.7% less than threshold-triggered summarization. Their AKV serving engine adds up to 1.2x throughput and 1.5x faster P95 latency.
https://t.co/fks8lJ46P3
Chat with Paper: https://t.co/wnCyl6Oxqi
