Saved in:
Bibliographic Details
Main Authors: Zhao, Qingfei, Wang, Ruobing, Xu, Dingling, Zha, Daren, Liu, Limin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.04185
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910987387404288
author Zhao, Qingfei
Wang, Ruobing
Xu, Dingling
Zha, Daren
Liu, Limin
author_facet Zhao, Qingfei
Wang, Ruobing
Xu, Dingling
Zha, Daren
Liu, Limin
contents Large language models (LLMs) have notably progressed in multi-step and long-chain reasoning. However, extending their reasoning capabilities to encompass deep interactions with search remains a non-trivial challenge, as models often fail to identify optimal reasoning-search interaction trajectories, resulting in suboptimal responses. We propose R-Search, a novel reinforcement learning framework for Reasoning-Search integration, designed to enable LLMs to autonomously execute multi-step reasoning with deep search interaction, and learn optimal reasoning search interaction trajectories via multi-reward signals, improving response quality in complex logic- and knowledge-intensive tasks. R-Search guides the LLM to dynamically decide when to retrieve or reason, while globally integrating key evidence to enhance deep knowledge interaction between reasoning and search. During RL training, R-Search provides multi-stage, multi-type rewards to jointly optimize the reasoning-search trajectory. Experiments on seven datasets show that R-Search outperforms advanced RAG baselines by up to 32.2% (in-domain) and 25.1% (out-of-domain). The code and data are available at https://github.com/QingFei1/R-Search.
format Preprint
id arxiv_https___arxiv_org_abs_2506_04185
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning
Zhao, Qingfei
Wang, Ruobing
Xu, Dingling
Zha, Daren
Liu, Limin
Computation and Language
Large language models (LLMs) have notably progressed in multi-step and long-chain reasoning. However, extending their reasoning capabilities to encompass deep interactions with search remains a non-trivial challenge, as models often fail to identify optimal reasoning-search interaction trajectories, resulting in suboptimal responses. We propose R-Search, a novel reinforcement learning framework for Reasoning-Search integration, designed to enable LLMs to autonomously execute multi-step reasoning with deep search interaction, and learn optimal reasoning search interaction trajectories via multi-reward signals, improving response quality in complex logic- and knowledge-intensive tasks. R-Search guides the LLM to dynamically decide when to retrieve or reason, while globally integrating key evidence to enhance deep knowledge interaction between reasoning and search. During RL training, R-Search provides multi-stage, multi-type rewards to jointly optimize the reasoning-search trajectory. Experiments on seven datasets show that R-Search outperforms advanced RAG baselines by up to 32.2% (in-domain) and 25.1% (out-of-domain). The code and data are available at https://github.com/QingFei1/R-Search.
title R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning
topic Computation and Language
url https://arxiv.org/abs/2506.04185