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

arXiv: https://arxiv.org/abs/2505.23794 · HTML: https://mlsanity.com/paper/2505.23794/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 29 of its 36 references that are in the map.
- First posted on arXiv 26 May 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)
- Retrieval-augmented generation / [Agentic RAG, agents and memory](https://mlsanity.com/rag/agentic-rag-agents-and-memory/)

## Builds on (most cited first, 29 of 29)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?](https://mlsanity.com/paper/2504.13837/) (2025)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [Active Retrieval Augmented Generation](https://mlsanity.com/paper/2305.06983/) (2023)
- [Search-o1: Agentic Search-Enhanced Large Reasoning Models](https://mlsanity.com/paper/2501.05366/) (2025)
- [Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy](https://mlsanity.com/paper/2305.15294/) (2023)
- [R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.05592/) (2025)
- [DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments](https://mlsanity.com/paper/2504.03160/) (2025)
- [FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research](https://mlsanity.com/paper/2405.13576/) (2024)
- [ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.19470/) (2025)
- [BM25S: Orders of magnitude faster lexical search via eager sparse scoring](https://mlsanity.com/paper/2407.03618/) (2024)
- [OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework](https://mlsanity.com/paper/2405.11143/) (2024)
- [Auto-RAG: Autonomous Retrieval-Augmented Generation for Large Language Models](https://mlsanity.com/paper/2411.19443/) (2024)
- [S2R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning](https://mlsanity.com/paper/2502.12853/) (2025)
- [DeepRAG: Thinking to Retrieve Step by Step for Large Language Models](https://mlsanity.com/paper/2502.01142/) (2025)

## Built on by (most cited first, 20 of 20)

- [A Technical Survey of Reinforcement Learning Techniques for Large Language Models](https://mlsanity.com/paper/2507.04136/) (2025)
- [Large Reasoning Embedding Models: Towards Next-Generation Dense Retrieval Paradigm](https://mlsanity.com/paper/2510.14321/) (2025)
- [Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization](https://mlsanity.com/paper/2604.14267/) (2026)
- [Towards Global Retrieval Augmented Generation: A Benchmark for Corpus-Level Reasoning](https://mlsanity.com/paper/2510.26205/) (2025)
- [Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation](https://mlsanity.com/paper/2602.09305/) (2026)
- [From Sufficiency to Reflection: Reinforcement-Guided Thinking Quality in Retrieval-Augmented Reasoning for LLMs](https://mlsanity.com/paper/2507.22716/) (2025)
- [Knowing When to Ask: Segment-Level Credit Assignment for LLM Tool Use](https://mlsanity.com/paper/2605.27788/) (2026)
- [REX-RAG: Reasoning Exploration with Policy Correction in Retrieval-Augmented Generation](https://mlsanity.com/paper/2508.08149/) (2025)
- [Fast, Slow, and Tool-augmented Thinking for LLMs: A Review](https://mlsanity.com/paper/2508.12265/) (2025)
- [Multi-hop Reasoning via Early Knowledge Alignment](https://mlsanity.com/paper/2512.20144/) (2025)
- [Mitigating Hallucination in Financial Retrieval-Augmented Generation via Fine-Grained Knowledge Verification](https://mlsanity.com/paper/2602.05723/) (2026)
- [AdaptR1: Reinforcement Learning Based Adaptive Interleaved Thinking in Multi-hop Question Answering](https://mlsanity.com/paper/2605.31062/) (2026)
- [Learning to Reason by Analogy via Retrieval-Augmented Reinforcement Fine-Tuning](https://mlsanity.com/paper/2606.13680/) (2026)
- [Stateful Evidence-Driven Retrieval-Augmented Generation with Iterative Reasoning](https://mlsanity.com/paper/2604.14170/) (2026)
- [Integrating Chain-of-Thought into Generative Retrieval: A Preliminary Study](https://mlsanity.com/paper/2605.22358/) (2026)
- [C-MIG: Multi-view Information Gain-based Retrieval-Augmented Generation for Clinical Diagnosis Reasoning](https://mlsanity.com/paper/2605.27860/) (2026)
- [Principled Top-k Selection for Language Models with Hybrid Gradients](https://mlsanity.com/paper/2610.04162/) (2026)
- [Beyond Outcome Rewards: Constructing and Assigning Retrieval Credit for Search Agents](https://mlsanity.com/paper/2610.10179/) (2026)
- [SignRAG: Unified Retrieval-Augmented Gloss-Free Sign Language Translation](https://mlsanity.com/paper/2610.11371/) (2026)
- [Project Greenhouse: Progress Toward Fully Open and Sovereign Agentic Search](https://mlsanity.com/paper/2610.11922/) (2026)

## Abstract (arXiv)

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 R3-RAG, which uses Reinforcement learning to make the LLM learn how to Reason and Retrieve 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.