Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

HyperMem: Hypergraph Memory for Long-Term Conversations

Juwei Yue, Chuanrui Hu, Jiawei Sheng, Zuyi Zhou, Wenyuan Zhang, Tingwen Liu, Li Guo, Yafeng Deng

Abstract

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.

HyperMem: Hypergraph Memory for Long-Term Conversations

Abstract

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.

Paper Structure

This paper contains 42 sections, 4 equations, 13 figures, 2 tables, 3 algorithms.

Table of Contents

  1. Introduction
  2. Related works
  3. Retrieval-Augmented Generation
  4. Memory System of Agents
  5. Approach
  6. Hypergraph Memory Structure
  7. Hypergraph Memory Construction
  8. Episode Detection
  9. Method.
  10. Remark.
  11. Topic Aggregation
  12. Method.
  13. Remark.
  14. Fact Extraction
  15. Method.
  16. ...and 27 more sections

Figures (13)

  • Figure 1: Memory structure comparison across Chunk-based RAG, Graph-based RAG, and our HyperMem.
  • Figure 2: Framework of HyperMem. The indexing detects episode boundaries, aggregates topics via hyperedges, and extracts facts. The retrieval performs coarse-to-fine search from topics to episodes to facts.
  • Figure 3: Ablation study across four question categories. FC: Fact context. EC: Episode context. TR: Topic-level retrieval. ER: Episode-level retrieval. The shaded region highlights the full HyperMem configuration.
  • Figure 4: Hyperparameter sensitivity analysis on LoCoMo. We evaluate the impact of embedding fusion weight $\alpha$ and Top-k selection at each hierarchical level (Topic, Episode, Fact) on retrieval performance.
  • Figure 5: Token usage vs. accuracy comparison. The x-axis shows relative token usage (Mem0 as 1.0$\times$ baseline), and the y-axis shows LLM-as-a-judge accuracy.
  • ...and 8 more figures