R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning

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 reasoningsearch 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 multistep 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 search or reason, while globally integrating key evidence to enhance deep knowledge interaction between reasoning and search.During RL training, R-Search provides multi-type rewards to jointly optimize the reasoning-search trajectory.Experiments on seven datasets show that R-Search significantly outperforms mainstream RAG baselines.The code and data are available at https://github.com/QingFei1/ R-Search.