IndexRAG shifts cross-document reasoning from inference-time prompting to offline indexing by generating 'bridging facts' at index time.
March 18, 2026
Original Paper
IndexRAG: Bridging Facts for Cross-Document Reasoning at Index Time
arXiv · 2603.16415
The Takeaway
It enables multi-hop reasoning using only single-pass retrieval and a single LLM call, outperforming complex graph-based RAG methods. This significantly reduces latency and compute costs for complex question-answering pipelines.
From the abstract
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 u