让大模型像人一样有结构化记忆，记事更连贯
Structured Episodic Event Memory
- 用图结构存关系，用动态记忆记事件顺序
- 在两个评测集上表现优于现有方法，叙事更连贯
- 适合需要长期记忆的智能体任务，如对话系统
当前大型语言模型的记忆机制主要依赖静态的检索增强生成（RAG），常导致检索碎片化，难以捕捉复杂推理所需的结构依赖。对于自主智能体而言，这种被动且扁平的架构缺乏建模长期交互动态与关联性的认知组织能力。为此，我们提出结构化情景事件记忆（SEEM），一种融合图记忆层与动态情景记忆层的分层框架。基于认知框架理论，SEEM将交互流转化为由精确溯源指针锚定的结构化情景事件框架（EEF）。此外，我们引入代理关联融合与反向溯源扩展（RPE）机制，从零散证据中重构连贯的情景上下文。在LoCoMo和LongMemEval基准上的实验结果表明，SEEM显著优于基线方法，使智能体在叙事连贯性与逻辑一致性方面表现更优。
原文摘要 · Abstract (English)
Current approaches to memory in Large Language Models (LLMs) predominantly rely on static Retrieval-Augmented Generation (RAG), which often results in scattered retrieval and fails to capture the structural dependencies required for complex reasoning. For autonomous agents, these passive and flat architectures lack the cognitive organization necessary to model the dynamic and associative nature of long-term interaction. To address this, we propose Structured Episodic Event Memory (SEEM), a hierarchical framework that synergizes a graph memory layer for relational facts with a dynamic episodic memory layer for narrative progression. Grounded in cognitive frame theory, SEEM transforms interaction streams into structured Episodic Event Frames (EEFs) anchored by precise provenance pointers. Furthermore, we introduce an agentic associative fusion and Reverse Provenance Expansion (RPE) mechanism to reconstruct coherent narrative contexts from fragmented evidence. Experimental results on the LoCoMo and LongMemEval benchmarks demonstrate that SEEM significantly outperforms baselines, enabling agents to maintain superior narrative coherence and logical consistency.
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。