MemForest：通过事件树划分与渐进合并实现高效智能体记忆管理
MemForest: Efficient Agent Memory Management via EventTree Partitioning and Progressive Merging
浏览论文内容
中文总结 AI 辅助
MemForest通过事件树划分与渐进合并压缩智能体历史记忆，在保留高比例性能的同时实现显著存储降低与检索加速。
中文摘要 AI 辅助
智能体记忆系统在长期对话、个性化助手和视频理解方面已展现出显著潜力。然而，持续累积的记忆在推理过程中会引入大量的存储和检索成本。为解决这一问题，我们提出了MemForest，一个可适配各种智能体记忆系统的通用记忆压缩框架。具体而言，MemForest通过利用全局语义相似性和局部时间连续性，将历史记忆划分为以事件为中心的单元。对于每个单元，它构建一棵最大生成树，称为事件树（EventTree），并通过选择高权重边来渐进合并冗余记忆节点，从而降低存储开销。此外，我们引入了一种锚点引导的传播检索机制，该机制从关键节点的时间邻域中检索相关记忆节点，提高了检索准确性。大量实验证明了MemForest的有效性。在单模态Mem0框架下，MemForest在三个基准（LoCoMo、LongMemEval和PersonaMem）上压缩了50%的历史记忆，同时保留了97.1%的原始性能，实现了1.89倍的检索加速。在多模态M3-Agent框架下，它在两个基准（M3-Bench-robot和M3-Bench-web）上以50%的压缩率保留了99.7%的原始性能，实现了2.24倍的检索加速。我们的代码可在[此https URL]获取。
英文摘要
Agent memory systems have demonstrated significant potential in long-term dialogue, personalized assistants, and video understanding. However, continuously accumulated memory introduces substantial storage and retrieval costs during inference. To address this issue, we propose \textbf{MemForest}, a general memory compression framework adaptable to various agent memory systems. Specifically, MemForest partitions historical memory into event-centric units by leveraging global semantic similarity and local temporal continuity. For each unit, it constructs a maximum spanning tree, termed an EventTree, and progressively merges redundant memory nodes by selecting high-weight edges, reducing storage overhead. Furthermore, we introduce an anchor-guided propagation retrieval mechanism that retrieves relevant memory nodes from the temporal neighborhoods of key nodes, improving retrieval accuracy. Extensive experiments demonstrate the effectiveness of MemForest. Under the unimodal Mem0 framework, MemForest retains \textbf{97.1%} of the original performance while compressing \textbf{50%} of historical memory across three benchmarks (LoCoMo, LongMemEval, and PersonaMem), achieving a \textbf{1.89x} retrieval speedup. Under the multimodal M3-Agent framework, it preserves \textbf{99.7%} of the original performance with a \textbf{50%} compression ratio across two benchmarks (M3-Bench-robot and M3-Bench-web), achieving a \textbf{2.24x} retrieval speedup. \textcolor{RoyalBlue}{\textit{Our code is available at [https://github.com/Celina-love-sweet/MemForest.}}](https://github.com/Celina-love-sweet/MemForest.}})
发表机构
- Shanghai Jiao Tong University（上海交通大学）
- Fudan University（复旦大学）
- Nanjing University（南京大学）
- HIT（哈尔滨工业大学）
- Sichuan University（四川大学）
- Shanghai AI Laboratory（上海人工智能实验室）
- Alibaba Group（阿里巴巴集团）
- Tsinghua University（清华大学）
机构由 AI 辅助整理，请以论文原文为准。
