Conference paper · 2025 · Open access
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
neural information processing systems, 94974–94994 · Published 1 January 2025 · DOI 10.52202/085713-2858
In brief
“ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning” is a 2025 conference paper by Mingyang Chen and 12 co-authors, published in neural information processing systems. OpenAlex counts 320 citations as of 15 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 320
- Most cited in
- 2026 (194)
- Field-weighted impact
- 169.03
- References
- 2
- Authors
- 13
Abstract
Large Language Models (LLMs) have shown remarkable capabilities in reasoning, exemplified by the success of OpenAI-o1 and DeepSeek-R1. However, integrating reasoning with external search processes remains challenging, especially for complex multi-hop questions requiring multiple retrieval steps. We propose ReSearch, a novel framework that trains LLMs to Reason with Search via reinforcement learning without using any supervised data on reasoning steps. Our approach treats search operations as integral components of the reasoning chain, where when and how to perform searches is guided by text-based thinking, and search results subsequently influence further reasoning. We train ReSearch on Qwen2.5-7B(-Instruct) and Qwen2.5-32B(-Instruct) models and conduct extensive experiments. Despite being trained on only one dataset, our models demonstrate strong generalizability across various benchmarks. Analysis reveals that ReSearch naturally elicits advanced reasoning capabilities such as reflection and self-correction during the reinforcement learning process.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Chen, M., Sun, L., Li, T., Sun, H., Zhou, Y., Zhu, C., Wang, H., Pan, J. Z., Zhang, W., Chen, H., Yang, F., Zhou, Z., & Chen, W. (2025). ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning. neural information processing systems, 94974–94994. https://doi.org/10.52202/085713-2858
MLA 9
Chen, Mingyang, et al. “ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning.” neural information processing systems, 2025, pp. 94974–94994. https://doi.org/10.52202/085713-2858.
Chicago
Chen, Mingyang, Linzhuang Sun, Tianpeng Li, Haoze Sun, Yijie Zhou, Chenzheng Zhu, Haofen Wang, et al. 2025. “ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning.” neural information processing systems: 94974–94994. https://doi.org/10.52202/085713-2858.
Harvard
Chen, M. et al. (2025) ‘ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning’, neural information processing systems, pp. 94974–94994. doi:10.52202/085713-2858.
IEEE
M. Chen et al., “ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning,” neural information processing systems, pp. 94974–94994, 2025, doi: 10.52202/085713-2858.
BibTeX
@inproceedings{chen2025research,
title = {{ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning}},
author = {Chen, Mingyang and Sun, Linzhuang and Li, Tianpeng and Sun, Haoze and Zhou, Yijie and Zhu, Chenzheng and Wang, Haofen and Pan, Jeff Z. and Zhang, Wen and Chen, Huajun and Yang, Fan and Zhou, Zenan and Chen, Weipeng},
booktitle = {neural information processing systems},
year = {2025},
pages = {94974--94994},
doi = {10.52202/085713-2858},
url = {https://doi.org/10.52202/085713-2858}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2024 | 1 | |
| 2025 | 125 | |
| 2026 | 194 |
Its field-weighted citation impact is 169.03: it has been cited 169.03 times as often as the average work of the same field, type and year (1.00 is the world average).
Topic and keywords
Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- large language models
- multi-hop question answering
- external search
- retrieval-augmented reasoning
- reinforcement learning from human feedback
- search planning
- self-correction
- reflection
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Chen, M., Sun, L., Li, T., Sun, H., Zhou, Y., Zhu, C., Wang, H., Pan, J. Z., Zhang, W., Chen, H., Yang, F., Zhou, Z., & Chen, W. (2025). ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning. neural information processing systems, 94974–94994. https://doi.org/10.52202/085713-2858
How many times has this paper been cited?
320 times, according to OpenAlex on 15 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access: read the free full text at arXiv (Cornell University).
Who wrote this paper?
Mingyang Chen, Linzhuang Sun, Tianpeng Li, Haoze Sun, Yijie Zhou, Chenzheng Zhu, Haofen Wang, Jeff Z. Pan, Wen Zhang, Huajun Chen, Fan Yang, Zenan Zhou and 1 more.
What is the DOI of this paper?
10.52202/085713-2858. The permanent link is https://doi.org/10.52202/085713-2858.
Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.