{"ID":2826741,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.18329","arxiv_id":"2512.18329","title":"LIR$^3$AG: A Lightweight Rerank Reasoning Strategy Framework for Retrieval-Augmented Generation","abstract":"Retrieval-Augmented Generation (RAG) effectively enhances Large Language Models (LLMs) by incorporating retrieved external knowledge into the generation process. Reasoning models improve LLM performance in multi-hop QA tasks, which require integrating and reasoning over multiple pieces of evidence across different documents to answer a complex question. However, they often introduce substantial computational costs, including increased token consumption and inference latency. To better understand and mitigate this trade-off, we conduct a comprehensive study of reasoning strategies for reasoning models in RAG multi-hop QA tasks. Our findings reveal that reasoning models adopt structured strategies to integrate retrieved and internal knowledge, primarily following two modes: Context-Grounded Reasoning, which relies directly on retrieved content, and Knowledge-Reconciled Reasoning, which resolves conflicts or gaps using internal knowledge. To this end, we propose a novel Lightweight Rerank Reasoning Strategy Framework for RAG (LiR$^3$AG) to enable non-reasoning models to transfer reasoning strategies by restructuring retrieved evidence into coherent reasoning chains. LiR$^3$AG significantly reduce the average 98% output tokens overhead and 58.6% inferencing time while improving 8B non-reasoning model's F1 performance ranging from 6.2% to 22.5% to surpass the performance of 32B reasoning model in RAG, offering a practical and efficient path forward for RAG systems.","short_abstract":"Retrieval-Augmented Generation (RAG) effectively enhances Large Language Models (LLMs) by incorporating retrieved external knowledge into the generation process. Reasoning models improve LLM performance in multi-hop QA tasks, which require integrating and reasoning over multiple pieces of evidence across different docu...","url_abs":"https://arxiv.org/abs/2512.18329","url_pdf":"https://arxiv.org/pdf/2512.18329v2","authors":"[\"Guo Chen\",\"Junjie Huang\",\"Huaijin Xie\",\"Fei Sun\",\"Tao Jia\"]","published":"2025-12-20T11:53:37Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"RAG\",\"Large Language Model\",\"Language Model\"]","has_code":false}