HyperMem: Hypergraph Memory for Long-Term Conversations
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918437718065152 |
|---|---|
| author | Yue, Juwei Hu, Chuanrui Sheng, Jiawei Zhou, Zuyi Zhang, Wenyuan Liu, Tingwen Guo, Li Deng, Yafeng |
| author_facet | Yue, Juwei Hu, Chuanrui Sheng, Jiawei Zhou, Zuyi Zhang, Wenyuan Liu, Tingwen Guo, Li Deng, Yafeng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_08256 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | HyperMem: Hypergraph Memory for Long-Term Conversations Yue, Juwei Hu, Chuanrui Sheng, Jiawei Zhou, Zuyi Zhang, Wenyuan Liu, Tingwen Guo, Li Deng, Yafeng Computation and Language Artificial Intelligence 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. |
| title | HyperMem: Hypergraph Memory for Long-Term Conversations |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2604.08256 |