用超图结构整合对话记忆，让长对话更连贯。
HyperMem: Hypergraph Memory for Long-Term Conversations
- 用超边建模多元素关联，突破传统成对关系限制。
- 在LoCoMo上达92.73%评分，显著提升长程对话准确率。
- 适合需要持久记忆的智能客服与个性化助手场景。
长期记忆对对话代理维持连贯性、追踪持续任务和实现个性化交互至关重要。然而，现有基于检索增强生成（RAG）和图结构记忆的方法大多依赖成对关系，难以捕捉多元素间的高阶关联（即联合依赖），导致检索碎片化。为此，我们提出HyperMem，一种基于超图的分层记忆架构，通过超边显式建模此类关联。HyperMem将记忆分为主题、事件和事实三层，利用超边将相关事件及其事实分组，将分散内容统一为连贯单元。基于该结构，设计混合词法-语义索引与粗粒度到细粒度的检索策略，支持高阶关联的精准高效检索。在LoCoMo基准测试中，HyperMem达到92.73%的LLM-as-a-judge准确率，证明其在长时对话中的有效性。
原文摘要 · Abstract (English)
Long-term memory is essential for conversational agents to maintain coherence, track persistent tasks, and provide personalized interactions across extended dialogues. However, existing approaches as Retrieval-Augmented Generation (RAG) and graph-based memory mostly rely on pairwise relations, which can hardly capture high-order associations, i.e., joint dependencies among multiple elements, causing fragmented retrieval. To this end, we propose HyperMem, a hypergraph-based hierarchical memory architecture that explicitly models such associations using hyperedges. Particularly, HyperMem structures memory into three levels: topics, episodes, and facts, and groups related episodes and their facts via hyperedges, unifying scattered content into coherent units. Leveraging this structure, we design a hybrid lexical-semantic index and a coarse-to-fine retrieval strategy, supporting accurate and efficient retrieval of high-order associations. Experiments on the LoCoMo benchmark show that HyperMem achieves state-of-the-art performance with 92.73% LLM-as-a-judge accuracy, demonstrating the effectiveness of HyperMem for long-term conversations.
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。