Cover Image

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:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MARAG-R1: Beyond Single Retriever via Reinforcement-Learned Multi-Tool Agentic Retrieval
by: Luo, Qi, et al.
Published: (2025)

Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective
by: Zeng, Zhiyuan, et al.
Published: (2024)

Zero-RAG: Towards Retrieval-Augmented Generation with Zero Redundant Knowledge
by: Luo, Qi, et al.
Published: (2025)

Unified Active Retrieval for Retrieval Augmented Generation
by: Cheng, Qinyuan, et al.
Published: (2024)

LLatrieval: LLM-Verified Retrieval for Verifiable Generation
by: Li, Xiaonan, et al.
Published: (2023)

BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning
by: Li, Yuan, et al.
Published: (2026)

Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?
by: Zeng, Zhiyuan, et al.
Published: (2025)

Towards Global Retrieval Augmented Generation: A Benchmark for Corpus-Level Reasoning
by: Luo, Qi, et al.
Published: (2025)

Multi-hop Reasoning via Early Knowledge Alignment
by: Wang, Yuxin, et al.
Published: (2025)

Dynamic and Generalizable Process Reward Modeling
by: Yin, Zhangyue, et al.
Published: (2025)

Aggregation of Reasoning: A Hierarchical Framework for Enhancing Answer Selection in Large Language Models
by: Yin, Zhangyue, et al.
Published: (2024)

StepPO: Step-Aligned Policy Optimization for Agentic Reinforcement Learning
by: Wang, Daoyu, et al.
Published: (2026)

FamilyTool: A Multi-hop Personalized Tool Use Benchmark
by: Wang, Yuxin, et al.
Published: (2025)

VehicleWorld: A Highly Integrated Multi-Device Environment for Intelligent Vehicle Interaction
by: Yang, Jie, et al.
Published: (2025)

RLoop: An Self-Improving Framework for Reinforcement Learning with Iterative Policy Initialization
by: Zhiyuan, Zeng, et al.
Published: (2025)

AdaptR1: Reinforcement Learning Based Adaptive Interleaved Thinking in Multi-hop Question Answering
by: Wang, Yuxin, et al.
Published: (2026)

Can Language Models Learn to Skip Steps?
by: Liu, Tengxiao, et al.
Published: (2024)

Rewarding What Matters: Step-by-Step Reinforcement Learning for Task-Oriented Dialogue
by: Du, Huifang, et al.
Published: (2024)

Scaling Laws for Fact Memorization of Large Language Models
by: Lu, Xingyu, et al.
Published: (2024)

Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration
by: Sun, Qiushi, et al.
Published: (2023)

Stop Rewarding Hallucinated Steps: Faithfulness-Aware Step-Level Reinforcement Learning for Small Reasoning Models
by: Nie, Shuo, et al.
Published: (2026)

StepTool: Enhancing Multi-Step Tool Usage in LLMs via Step-Grained Reinforcement Learning
by: Yu, Yuanqing, et al.
Published: (2024)

REARANK: Reasoning Re-ranking Agent via Reinforcement Learning
by: Zhang, Le, et al.
Published: (2025)

Agent Alignment in Evolving Social Norms
by: Li, Shimin, et al.
Published: (2024)

Boosting Maximum Entropy Reinforcement Learning via One-Step Flow Matching
by: Li, Zeqiao, et al.
Published: (2026)

How to Mitigate Overfitting in Weak-to-strong Generalization?
by: Shi, Junhao, et al.
Published: (2025)

Can AI Assistants Know What They Don't Know?
by: Cheng, Qinyuan, et al.
Published: (2024)

RAISE: Enhancing Scientific Reasoning in LLMs via Step-by-Step Retrieval
by: Oh, Minhae, et al.
Published: (2025)

StepCodeReasoner: Aligning Code Reasoning with Stepwise Execution Traces via Reinforcement Learning
by: Wang, Hao, et al.
Published: (2026)

StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason
by: Zhang, Kaiyi, et al.
Published: (2025)

Unleashing Embodied Task Planning Ability in LLMs via Reinforcement Learning
by: Fei, Zhaoye, et al.
Published: (2025)

Reinforcing Compositional Retrieval: Retrieving Step-by-Step for Composing Informative Contexts
by: Long, Quanyu, et al.
Published: (2025)

Offline Reinforcement Learning for LLM Multi-Step Reasoning
by: Wang, Huaijie, et al.
Published: (2024)

ConvSearch-R1: Enhancing Query Reformulation for Conversational Search with Reasoning via Reinforcement Learning
by: Zhu, Changtai, et al.
Published: (2025)

Teaching LLMs for Step-Level Automatic Math Correction via Reinforcement Learning
by: Li, Junsong, et al.
Published: (2025)

Two-Step Offline Preference-Based Reinforcement Learning with Constrained Actions
by: Xu, Yinglun, et al.
Published: (2023)

$S^3$-R1: Learning to Retrieve and Answer Step-by-Step with Synthetic Data
by: Goel, Harsh, et al.
Published: (2026)

DeepRAG: Thinking to Retrieve Step by Step for Large Language Models
by: Guan, Xinyan, et al.
Published: (2025)

Agentic Reinforcement Learning with Implicit Step Rewards
by: Liu, Xiaoqian, et al.
Published: (2025)

Let's Be Self-generated via Step by Step: A Curriculum Learning Approach to Automated Reasoning with Large Language Models
by: Luo, Kangyang, et al.
Published: (2024)