不依赖大模型生成，直接保存对话原始内容并构建多锚点图谱。
EdgeMem: LLM-Free Agent Memory Construction and Retrieval via Evidence-Preserving Multi-Anchor Hypergraph
- 用多锚点超图结构组织原始对话，保留完整信息
- 在LoCoMo数据集上严格评分达61.01，优于其他7个系统
- 无需调用大模型即可完成记忆构建与检索，效率更高
Agent记忆使大模型代理在回答新问题时能利用先前的交互。现有方法常将交互历史压缩为摘要或大模型生成的表示，重复生成增加成本且可能提前丢失关键信息。我们提出EdgeMem，基于一个简单原则：保留原始交互回合，并通过互补内容、时间与情景线索进行组织。该方法通过轻量级本地处理构建多锚点超图，检索直接返回原始证据，将大模型用于最终答案生成，结合了多会话历史的结构化访问与原始对话的忠实保留。在LoCoMo和LongMemEval-S上的实验表明，该方法在检索与记忆引导问答中表现优异；在LoCoMo上，相较于七个复现系统，在统一提示下取得最高严格评分（61.01对比58.70），且构建与检索均无需生成式大模型调用。整体而言，保留并组织源证据为代理记忆提供了高效有效的基础，无需生成式记忆管理。
原文摘要 · Abstract (English)
Agent memory allows LLM agents to use earlier interactions when answering new queries. Existing methods often compress interaction histories into summaries or other LLM-generated representations. Repeated generation adds cost and can discard answer-bearing details before the system knows what a future query will require. We propose EdgeMem, an agent-memory method built around a simple principle: preserve original interaction turns and organize them through complementary content, temporal, and episodic cues. EdgeMem realizes this principle with a multi-anchor hypergraph constructed by lightweight local processing. Retrieval directly returns source evidence and reserves LLM use for final answer generation, combining structured access to multi-session histories with faithful retention of the original conversation. Experiments on LoCoMo and LongMemEval-S show strong retrieval and memory-grounded question answering; on LoCoMo, EdgeMem achieves the highest strict-judge score among seven reproduced systems under a shared prompt (61.01 versus 58.70), while construction and retrieval require no generative-LLM calls. Overall, EdgeMem shows that preserving and organizing source evidence provides an effective and efficient foundation for agent memory without generative memory management.
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。