Preprint · 2025 · Open access
A Survey of Reinforcement Learning for Large Reasoning Models
arXiv (Cornell University) · Published 10 September 2025 · DOI 10.48550/arxiv.2509.08827
In brief
“A Survey of Reinforcement Learning for Large Reasoning Models” is a 2025 preprint by Kaiyan Zhang and 38 co-authors, published in arXiv (Cornell University). OpenAlex counts 233 citations as of 15 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 233
- Most cited in
- 2026 (176)
- References
- 574
- Authors
- 39
Abstract
In this paper, we survey recent advances in Reinforcement Learning (RL) for reasoning with Large Language Models (LLMs). RL has achieved remarkable success in advancing the frontier of LLM capabilities, particularly in addressing complex logical tasks such as mathematics and coding. As a result, RL has emerged as a foundational methodology for transforming LLMs into LRMs. With the rapid progress of the field, further scaling of RL for LRMs now faces foundational challenges not only in computational resources but also in algorithm design, training data, and infrastructure. To this end, it is timely to revisit the development of this domain, reassess its trajectory, and explore strategies to enhance the scalability of RL toward Artificial SuperIntelligence (ASI). In particular, we examine research applying RL to LLMs and LRMs for reasoning abilities, especially since the release of DeepSeek-R1, including foundational components, core problems, training resources, and downstream applications, to identify future opportunities and directions for this rapidly evolving area. We hope this review will promote future research on RL for broader reasoning models. Github: https://github.com/TsinghuaC3I/Awesome-RL-for-LRMs
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Zhang, K., Zuo, Y., Bingxiang, H., Sun, Y., Liu, R., Che, J., Fan, Y., Tian, K., Jia, G., Li, P., Fu, Y., Lv, X., Zhang, Y., Sihang, Z., Qu, S., Li, H., Wang, S., Wang, Y., Long, X., . . . Zhou, B. (2025). A Survey of Reinforcement Learning for Large Reasoning Models. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2509.08827
MLA 9
Zhang, Kaiyan, et al. “A Survey of Reinforcement Learning for Large Reasoning Models.” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2509.08827.
Chicago
Zhang, Kaiyan, Yuxin Zuo, He, Bingxiang, Youbang Sun, Runze Liu, Jiang, Che, Yu‐Chen Fan, et al. 2025. “A Survey of Reinforcement Learning for Large Reasoning Models.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2509.08827.
Harvard
Zhang, K. et al. (2025) ‘A Survey of Reinforcement Learning for Large Reasoning Models’, arXiv (Cornell University). doi:10.48550/arxiv.2509.08827.
IEEE
K. Zhang et al., “A Survey of Reinforcement Learning for Large Reasoning Models,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2509.08827.
BibTeX
@misc{zhang2025survey,
title = {{A Survey of Reinforcement Learning for Large Reasoning Models}},
author = {Zhang, Kaiyan and Zuo, Yuxin and Bingxiang, He, and Sun, Youbang and Liu, Runze and Che, Jiang, and Fan, Yu‐Chen and Tian, Kai and Jia, Guoli and Li, Pengfei and Fu, Yu and Lv, Xingtai and Zhang, Yuchen and Sihang, Zeng, and Qu, Shang and Li, Haozhan and Wang, Shijie and Wang, Yuru and Long, Xinwei and Liu, Fangfu and Xu, Xiangyang and Ma, Jiaze and Xuekai, Zhu, and Hua, Ermo and Liu, Yihao and Li, Zonglin and Chen, Huayu and Qu, Xiaoye and Li, Yafu and Chen, Weize and others},
howpublished = {arXiv (Cornell University)},
year = {2025},
doi = {10.48550/arxiv.2509.08827},
url = {https://doi.org/10.48550/arxiv.2509.08827}
}
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 | 56 | |
| 2026 | 176 |
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- reinforcement learning
- large language models
- large reasoning models
- LLM reasoning
- mathematical reasoning
- DeepSeek-R1
- superintelligence
- training data
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?
Zhang, K., Zuo, Y., Bingxiang, H., Sun, Y., Liu, R., Che, J., Fan, Y., Tian, K., Jia, G., Li, P., Fu, Y., Lv, X., Zhang, Y., Sihang, Z., Qu, S., Li, H., Wang, S., Wang, Y., Long, X., . . . Zhou, B. (2025). A Survey of Reinforcement Learning for Large Reasoning Models. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2509.08827
How many times has this paper been cited?
233 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?
Kaiyan Zhang, Yuxin Zuo, He, Bingxiang, Youbang Sun, Runze Liu, Jiang, Che, Yu‐Chen Fan, Kai Tian, Guoli Jia, Pengfei Li, Yu Fu, Xingtai Lv and 27 more.
What is the DOI of this paper?
10.48550/arxiv.2509.08827. The permanent link is https://doi.org/10.48550/arxiv.2509.08827.
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.