# CompactRAG: Reducing LLM Calls and Token Overhead in Multi-Hop Question Answering Source: [CompactRAG: Reducing LLM Calls and Token Overhead in Multi-Hop Question Answering]() Collection index: [llms.txt]() Data updated: 2026-02-07T05:00:14.331Z Authors: Hao Yang, Zhiyu Yang, Xupeng Zhang, Wei Wei, Yunjie Zhang, Lin Yang Published: 2026-02-05T14:52:06.000Z ## Abstract Retrieval-augmented generation (RAG) has become a key paradigm for knowledge-intensive question answering. However, existing multi-hop RAG systems remain inefficient, as they alternate between retrieval and reasoning at each step, resulting in repeated LLM calls, high token consumption, and unstable entity grounding across hops. We propose CompactRAG, a simple yet effective framework that decouples offline corpus restructuring from online reasoning. In the offline stage, an LLM reads the corpus once and converts it into an atomic QA knowledge base, which represents knowledge as minimal, fine-grained question-answer pairs. In the online stage, complex queries are decomposed and carefully rewritten to preserve entity consistency, and are resolved through dense retrieval followed by RoBERTa-based answer extraction. Notably, during inference, the LLM is invoked only twice in total - once for sub-question decomposition and once for final answer synthesis - regardless of the number of reasoning hops. Experiments on HotpotQA, 2WikiMultiHopQA, and MuSiQue demonstrate that CompactRAG achieves competitive accuracy while substantially reducing token consumption compared to iterative RAG baselines, highlighting a cost-efficient and practical approach to multi-hop reasoning over large knowledge corpora. The implementation is available at GitHub. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Multi-hop Question Answering on HotpotQA (EM, F1, Acc)](): Multi-hop Question Answering; HotpotQA; Exact Match (EM): 49.6. - [Multi-hop Question Answering on MuSiQue (EM, F1, Acc)](): Multi-hop Question Answering; MuSiQue; F1: 42.34. - [Multi-hop Question Answering on 2WikiMultiHopQA](): Multi-hop Question Answering; 2WikiMultihopQA; EM: 47.2. ## Original sources and implementation [Original paper]() [PDF]()