Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning

By Bowen Jin, Hansi Zeng, Zhenrui Yue, Dong Wang, Hamed Zamani, Jiawei Han. arXiv.org, 2025

1,234 citations recorded by the source corpus.

Efficiently acquiring external knowledge and up-to-date information is essential for effective reasoning and text generation in large language models (LLMs). Prompting advanced LLMs with reasoning capabilities to use search engines during inference is often suboptimal, as the LLM might not fully possess the capability on how to interact optimally with the search engine. This paper introduces Search-R1, an extension of reinforcement learning (RL) for reasoning frameworks where the LLM learns to autonomously generate (multiple) search queries during step-by-step reasoning with real-time retrieval. Search-R1 optimizes LLM reasoning trajectories with multi-turn search interactions, leveraging retrieved token masking for stable RL training and a simple outcome-based reward function. Experiments on seven question-answering datasets show that Search-R1 improves performance by 41% (Qwen2.5-7B) and 20% (Qwen2.5-3B) over various RAG baselines under the same setting. This paper further provides empirical insights into RL optimization methods, LLM choices, and response length dynamics in retrieval-augmented reasoning. The code and model checkpoints are available at https://github.com/PeterGriffinJin/Search-R1.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/1fcaafeb72142fe3d1a5d698a072d69778d244b0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Rongyao Fang
  2. Jingren Zhou
  3. Gökhan Tür
  4. Shuai Bai
  5. Hongru Wang
  6. Xiusi Chen
  7. Rui Men
  8. Qidong Huang

In Information Systems

  1. Jingren Zhou
  2. Gökhan Tür

Citations in the corpus