Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.08827 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914083468476416 |
|---|---|
| author | Zhang, Kaiyan Zuo, Yuxin He, Bingxiang Sun, Youbang Liu, Runze Jiang, Che Fan, Yuchen Tian, Kai Jia, Guoli Li, Pengfei Fu, Yu Lv, Xingtai Zhang, Yuchen Zeng, Sihang Qu, Shang Li, Haozhan Wang, Shijie Wang, Yuru Long, Xinwei Liu, Fangfu Xu, Xiang Ma, Jiaze Zhu, Xuekai Hua, Ermo Liu, Yihao Li, Zonglin Chen, Huayu Qu, Xiaoye Li, Yafu Chen, Weize Yuan, Zhenzhao Gao, Junqi Li, Dong Ma, Zhiyuan Cui, Ganqu Liu, Zhiyuan Qi, Biqing Ding, Ning Zhou, Bowen |
| author_facet | Zhang, Kaiyan Zuo, Yuxin He, Bingxiang Sun, Youbang Liu, Runze Jiang, Che Fan, Yuchen Tian, Kai Jia, Guoli Li, Pengfei Fu, Yu Lv, Xingtai Zhang, Yuchen Zeng, Sihang Qu, Shang Li, Haozhan Wang, Shijie Wang, Yuru Long, Xinwei Liu, Fangfu Xu, Xiang Ma, Jiaze Zhu, Xuekai Hua, Ermo Liu, Yihao Li, Zonglin Chen, Huayu Qu, Xiaoye Li, Yafu Chen, Weize Yuan, Zhenzhao Gao, Junqi Li, Dong Ma, Zhiyuan Cui, Ganqu Liu, Zhiyuan Qi, Biqing Ding, Ning Zhou, Bowen |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_08827 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Survey of Reinforcement Learning for Large Reasoning Models Zhang, Kaiyan Zuo, Yuxin He, Bingxiang Sun, Youbang Liu, Runze Jiang, Che Fan, Yuchen Tian, Kai Jia, Guoli Li, Pengfei Fu, Yu Lv, Xingtai Zhang, Yuchen Zeng, Sihang Qu, Shang Li, Haozhan Wang, Shijie Wang, Yuru Long, Xinwei Liu, Fangfu Xu, Xiang Ma, Jiaze Zhu, Xuekai Hua, Ermo Liu, Yihao Li, Zonglin Chen, Huayu Qu, Xiaoye Li, Yafu Chen, Weize Yuan, Zhenzhao Gao, Junqi Li, Dong Ma, Zhiyuan Cui, Ganqu Liu, Zhiyuan Qi, Biqing Ding, Ning Zhou, Bowen Computation and Language Artificial Intelligence Machine Learning 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 |
| title | A Survey of Reinforcement Learning for Large Reasoning Models |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2509.08827 |