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 training or fine-tuning. Experiments on three widely-used multi-hop QA benchmarks (HotpotQA, 2WikiMultiHopQA, MuSiQue) show that IndexRAG improves F1 over Naive RAG by 4.6 points on average, while requiring only single-pass retrieval and a single LLM call at inference time. When combined with IRCoT, IndexRAG outperforms all graph-based baselines on average, including HippoRAG and FastGraphRAG, while relying solely on flat retrieval. Our code will be released upon acceptance.

翻译：多跳问答（QA）需要跨多个文档进行推理，然而现有的检索增强生成（RAG）方法要么通过需要额外在线处理的基于图的方法，要么通过迭代的多步推理来解决此问题。我们提出了IndexRAG，这是一种新颖的方法，它将跨文档推理从在线推断转移到离线索引。IndexRAG识别跨文档共享的桥接实体，并生成可作为独立可检索单元的桥接事实，无需额外的训练或微调。在三个广泛使用的多跳问答基准（HotpotQA、2WikiMultiHopQA、MuSiQue）上的实验表明，IndexRAG在推理时仅需单次检索和一次LLM调用，其F1分数平均比Naive RAG提高了4.6分。当与IRCoT结合时，IndexRAG平均优于所有基于图的基线方法，包括HippoRAG和FastGraphRAG，同时仅依赖于扁平检索。我们的代码将在论文被接受后发布。