用多图结构分离记忆的语义、时间、因果和实体信息，提升长程推理准确性。
MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents
- 将记忆拆分为语义、时间、因果、实体四类独立图结构
- 通过策略引导遍历实现查询自适应检索，准确率显著提升
- 适合需要可解释推理路径的复杂任务场景
记忆增强生成（MAG）通过外部记忆扩展大语言模型的长上下文推理能力，但现有方法多依赖单一记忆库中的语义相似度，导致时间、因果与实体信息混杂，影响可解释性与查询意图匹配度，进而降低推理准确率。本文提出MAGMA，一种基于多图的智能体记忆架构，将每条记忆项在语义、时间、因果和实体四个正交图中分别表示。MAGMA将检索建模为策略引导的多关系图遍历，支持查询自适应选择与结构化上下文构建。通过解耦记忆表示与检索逻辑，MAGMA提供透明的推理路径和细粒度控制。在LoCoMo和LongMemEval数据集上的实验表明，MAGMA在长程推理任务中持续优于当前最优的智能体记忆系统。
原文摘要 · Abstract (English)
Memory-Augmented Generation (MAG) extends Large Language Models with external memory to support long-context reasoning, but existing approaches largely rely on semantic similarity over monolithic memory stores, entangling temporal, causal, and entity information. This design limits interpretability and alignment between query intent and retrieved evidence, leading to suboptimal reasoning accuracy. In this paper, we propose MAGMA, a multi-graph agentic memory architecture that represents each memory item across orthogonal semantic, temporal, causal, and entity graphs. MAGMA formulates retrieval as policy-guided traversal over these relational views, enabling query-adaptive selection and structured context construction. By decoupling memory representation from retrieval logic, MAGMA provides transparent reasoning paths and fine-grained control over retrieval. Experiments on LoCoMo and LongMemEval demonstrate that MAGMA consistently outperforms state-of-the-art agentic memory systems in long-horizon reasoning tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。