MemForest：一种具有层次化时间索引的高效智能体记忆系统

摘要

记忆是实现长上下文LLM代理的基础组件，通过持续的“服务-更新”生命周期支持跨交互的持久状态。尽管已有大量工作，现有系统仍因两大关键限制承受显著维护开销：粗粒度的状态管理与固有的顺序更新流水线。具体而言，更新往往与LLM推理紧密耦合且需要全状态重写，导致随着记忆积累而出现扩展性差、延迟增长的问题。为应对这些挑战，我们提出MemForest——一种将代理记忆重构为写高效时序数据管理问题的记忆框架。MemForest通过并行分块提取打破顺序瓶颈，将记忆构建解耦为并发独立操作。为进一步消除粗粒度维护，我们引入MemTree——一种分层时间索引，将记忆组织为时间有序树结构而非扁平全局摘要。该设计以局部化节点更新替代全状态重写，将维护开销降至受影响的树路径，同时自然保留随时间演变的状态。我们在两个长上下文记忆基准LongMemEval-S和LoCoMo上评估MemForest。在LongMemEval-S中，MemForest在有状态基线中取得最佳整体性能，达到79.8%的pass@1准确率，同时记忆构建吞吐量比包括EverMemOS在内的最先进方法高约6倍。

English

Memory is a fundamental component for enabling long-context LLM agents, supporting persistent state across interactions through a continuous serve-and-update lifecycle. Despite substantial prior work, existing systems suffer from significant maintenance overhead due to two key limitations: coarse-grained state management and inherently sequential update pipelines. In particular, updates are often tightly coupled with LLM inference and require full-state rewrites, leading to poor scalability and growing latency as memory accumulates. To address these challenges, we present MemForest, a memory framework that reformulates agent memory as a write-efficient temporal data management problem. MemForest breaks the sequential bottleneck via parallel chunk extraction, decoupling memory construction into concurrent, independent operations. To further eliminate coarse-grained maintenance, we introduce MemTree, a hierarchical temporal index that organizes memory as time-ordered trees rather than flat global summaries. This design replaces full-state rewrites with localized per-node updates, reducing maintenance cost to the affected tree paths while naturally preserving temporally evolving states. We evaluate MemForest on two long-context memory benchmarks, LongMemEval-S and LoCoMo. On LongMemEval-S, MemForest achieves the best overall performance among stateful baselines, reaching 79.8% pass@1 accuracy while sustaining a memory construction throughput approximately 6x higher than state-of-the-art approaches including EverMemOS.