HGMEM: Hypergraph-based Working Memory to Improve Multi-step RAG for Long-Context Complex Relational Modeling
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914606212972544 |
|---|---|
| author | Zhou, Chulun Zhang, Chunkang Yu, Guoxin Meng, Fandong Zhou, Jie Lam, Wai Yu, Mo |
| author_facet | Zhou, Chulun Zhang, Chunkang Yu, Guoxin Meng, Fandong Zhou, Jie Lam, Wai Yu, Mo |
| contents | Multi-step retrieval-augmented generation (RAG) has become a widely adopted strategy for enhancing large language models (LLMs) on tasks that demand global comprehension and intensive reasoning. Although many RAG systems incorporate a working memory to consolidate information, existing designs primarily function as a passive storage for isolated facts. This static nature overlooks crucial high-order correlations among primitive facts, thereby limiting models' capacity for multi-step reasoning and resulting in fragmented reasoning and weak global sense-making within extended contexts. We introduce HGMem, a hypergraph-based working memory system, extending the concept of memory beyond simple storage into a dynamic, expressive structure for complex reasoning and global understanding. In our approach, memory is represented as a hypergraph where hyperedges correspond to distinct memory units, enabling the progressive formation of high-order interactions within memory. This mechanism connects facts and thoughts around the focal problem, evolving the memory into an integrated and situated knowledge structure that provides strong propositions for deeper reasoning. We evaluate HGMem on several challenging global sense-making benchmarks. Extensive experiments and in-depth analyses demonstrate that our method consistently improves multi-step RAG and substantially outperforms strong baseline systems across diverse datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_23959 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HGMEM: Hypergraph-based Working Memory to Improve Multi-step RAG for Long-Context Complex Relational Modeling Zhou, Chulun Zhang, Chunkang Yu, Guoxin Meng, Fandong Zhou, Jie Lam, Wai Yu, Mo Computation and Language Artificial Intelligence Machine Learning Multi-step retrieval-augmented generation (RAG) has become a widely adopted strategy for enhancing large language models (LLMs) on tasks that demand global comprehension and intensive reasoning. Although many RAG systems incorporate a working memory to consolidate information, existing designs primarily function as a passive storage for isolated facts. This static nature overlooks crucial high-order correlations among primitive facts, thereby limiting models' capacity for multi-step reasoning and resulting in fragmented reasoning and weak global sense-making within extended contexts. We introduce HGMem, a hypergraph-based working memory system, extending the concept of memory beyond simple storage into a dynamic, expressive structure for complex reasoning and global understanding. In our approach, memory is represented as a hypergraph where hyperedges correspond to distinct memory units, enabling the progressive formation of high-order interactions within memory. This mechanism connects facts and thoughts around the focal problem, evolving the memory into an integrated and situated knowledge structure that provides strong propositions for deeper reasoning. We evaluate HGMem on several challenging global sense-making benchmarks. Extensive experiments and in-depth analyses demonstrate that our method consistently improves multi-step RAG and substantially outperforms strong baseline systems across diverse datasets. |
| title | HGMEM: Hypergraph-based Working Memory to Improve Multi-step RAG for Long-Context Complex Relational Modeling |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2512.23959 |