R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Yuan, Luo, Qi, Li, Xiaonan, Li, Bufan, Cheng, Qinyuan, Wang, Bo, Zheng, Yining, Wang, Yuxin, Yin, Zhangyue, Qiu, Xipeng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912669041164288
author Li, Yuan
Luo, Qi
Li, Xiaonan
Li, Bufan
Cheng, Qinyuan
Wang, Bo
Zheng, Yining
Wang, Yuxin
Yin, Zhangyue
Qiu, Xipeng
author_facet Li, Yuan
Luo, Qi
Li, Xiaonan
Li, Bufan
Cheng, Qinyuan
Wang, Bo
Zheng, Yining
Wang, Yuxin
Yin, Zhangyue
Qiu, Xipeng
contents Retrieval-Augmented Generation (RAG) integrates external knowledge with Large Language Models (LLMs) to enhance factual correctness and mitigate hallucination. However, dense retrievers often become the bottleneck of RAG systems due to their limited parameters compared to LLMs and their inability to perform step-by-step reasoning. While prompt-based iterative RAG attempts to address these limitations, it is constrained by human-designed workflows. To address these limitations, we propose $\textbf{R3-RAG}$, which uses $\textbf{R}$einforcement learning to make the LLM learn how to $\textbf{R}$eason and $\textbf{R}$etrieve step by step, thus retrieving comprehensive external knowledge and leading to correct answers. R3-RAG is divided into two stages. We first use cold start to make the model learn the manner of iteratively interleaving reasoning and retrieval. Then we use reinforcement learning to further harness its ability to better explore the external retrieval environment. Specifically, we propose two rewards for R3-RAG: 1) answer correctness for outcome reward, which judges whether the trajectory leads to a correct answer; 2) relevance-based document verification for process reward, encouraging the model to retrieve documents that are relevant to the user question, through which we can let the model learn how to iteratively reason and retrieve relevant documents to get the correct answer. Experimental results show that R3-RAG significantly outperforms baselines and can transfer well to different retrievers. We release R3-RAG at https://github.com/Yuan-Li-FNLP/R3-RAG.
format Preprint
id arxiv_https___arxiv_org_abs_2505_23794
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning
Li, Yuan
Luo, Qi
Li, Xiaonan
Li, Bufan
Cheng, Qinyuan
Wang, Bo
Zheng, Yining
Wang, Yuxin
Yin, Zhangyue
Qiu, Xipeng
Computation and Language
Artificial Intelligence
Retrieval-Augmented Generation (RAG) integrates external knowledge with Large Language Models (LLMs) to enhance factual correctness and mitigate hallucination. However, dense retrievers often become the bottleneck of RAG systems due to their limited parameters compared to LLMs and their inability to perform step-by-step reasoning. While prompt-based iterative RAG attempts to address these limitations, it is constrained by human-designed workflows. To address these limitations, we propose $\textbf{R3-RAG}$, which uses $\textbf{R}$einforcement learning to make the LLM learn how to $\textbf{R}$eason and $\textbf{R}$etrieve step by step, thus retrieving comprehensive external knowledge and leading to correct answers. R3-RAG is divided into two stages. We first use cold start to make the model learn the manner of iteratively interleaving reasoning and retrieval. Then we use reinforcement learning to further harness its ability to better explore the external retrieval environment. Specifically, we propose two rewards for R3-RAG: 1) answer correctness for outcome reward, which judges whether the trajectory leads to a correct answer; 2) relevance-based document verification for process reward, encouraging the model to retrieve documents that are relevant to the user question, through which we can let the model learn how to iteratively reason and retrieve relevant documents to get the correct answer. Experimental results show that R3-RAG significantly outperforms baselines and can transfer well to different retrievers. We release R3-RAG at https://github.com/Yuan-Li-FNLP/R3-RAG.
title R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2505.23794