AI 中文总结
CoEvo-Mem是协同演化检索策略与记忆库的闭环框架，通过交替更新路由器与记忆库，在七个基准测试中实现了大语言模型智能体的最先进性能。
AI 中文摘要
随着大语言模型（LLM）智能体在不同任务与会话中积累记忆，其长期性能同时依赖于查询特定的检索与持续的记忆优化。然而，现有方法通常仅优化记忆访问（如迭代查询优化或自适应检索策略）或记忆演化（如结构更新），这种分离忽略了一个核心反馈循环：检索决定了哪些记忆会获得使用信号，而更新后的记忆库会重塑未来的检索过程。我们提出CoEvo-Mem，这是一个用于协同演化检索策略与记忆库的闭环框架。对于每个查询，冻结的LLM会生成特定路由的查询重写和路由先验，轻量级残差路由器会在线修正这些内容。检索到的上下文是两个学习过程的耦合接口：任务结果为路由决策分配信用，而基于轨迹的反馈会更新记忆值与图关系。这些更新改变了后续查询的记忆排序与选择方式，从而闭合反馈循环。为缓解耦合引发的非平稳性，CoEvo-Mem交替执行两种操作：固定记忆库时更新路由器，固定检索策略时演化记忆库。在七个多样化基准测试中，CoEvo-Mem实现了最先进的性能，证明了检索-记忆协同演化的重要性。
英文摘要
As memories accumulate across tasks and sessions, the performance of long-term LLM agents depends jointly on query-specific retrieval and continual memory refinement. However, existing methods typically optimize either memory access, through iterative query refinement or adaptive retrieval policies, or memory evolution such as structural update. This separation overlooks a fundamental feedback loop: retrieval determines which memories receive usage signals, while updated memory bank reshape future retrieval. We propose \textbf{CoEvo-Mem}, a closed-loop framework for co-evolving the retrieval policy and memory bank. For each query, a frozen LLM generates route-specific query rewrites and a routing prior, which a lightweight residual router corrects online. The retrieved context serves as the coupling interface between the two learning processes: task outcomes assign credit to routing decisions, while trajectory-conditioned feedback updates memory values and graph relations. These updates alter how memories are ranked and selected for subsequent queries, thereby closing the feedback loop. To mitigate coupling induced non-stationarity, CoEvo-Mem alternates between updating the router with the memory bank fixed and evolving the memory bank with the retrieval policy fixed. Across seven diverse benchmarks, \textbf{CoEvo-Mem} achieves state-of-the-art performance, demonstrating the importance of retrieval-memory coevolution.
