HGMEM: Hypergraph-based Working Memory to Improve Multi-step RAG for Long-Context Complex Relational Modeling

ArXi:2512.23959v3 Announce Type: replace-cross 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.