AI RESEARCH
IndexRAG: Bridging Facts for Cross-Document Reasoning at Index Time
arXiv CS.AI
•
ArXi:2603.16415v1 Announce Type: cross Multi-hop question answering (QA) requires reasoning across multiple documents, yet existing retrieval-augmented generation (RAG) approaches address this either through graph-based methods requiring additional online processing or iterative multi-step reasoning. We present IndexRAG, a novel approach that shifts cross-document reasoning from online inference to offline indexing. IndexRAG identifies bridge entities shared across documents and generates bridging facts as independently retrievable units, requiring no additional.