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.

翻译：长期记忆对于对话智能体在扩展对话中维持连贯性、追踪持续性任务以及提供个性化交互至关重要。然而，现有方法如检索增强生成（RAG）和基于图的记忆大多依赖成对关系，难以捕捉高阶关联（即多个元素间的联合依赖关系），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。具体而言，HyperMem将记忆结构化为三个层次：主题、片段与事实，并通过超边将相关片段及其事实分组，将分散内容整合为连贯单元。依托该结构，我们设计了混合词汇-语义索引与由粗到细的检索策略，支持高阶关联的精准高效检索。在LoCoMo基准上的实验表明，HyperMem实现了92.73%的LLM-as-a-judge准确率，达到最先进性能，验证了其在长程对话中的有效性。