Conference paper · 2025 · Open access
Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective
neural information processing systems, 148885–148905 · Published 1 January 2025 · DOI 10.52202/085713-4479
In brief
“Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective” is a 2025 conference paper by Jorge (Zhoujun) Cheng and 23 co-authors, published in neural information processing systems. OpenAlex counts 0 citations as of 15 November 2026. It is open access under a CC BY-SA licence: the full text is free to read at neural information processing systems.
- Citations
- 0
- References
- 29
- Authors
- 24
Abstract
Reinforcement learning (RL) has shown promise in enhancing large language model (LLM) reasoning, yet progress towards broader capabilities is limited by the availability of high-quality, multi-domain datasets.This work introduces GURU, a 92K RL-for-reasoning dataset designed to address this gap, covering six reasoning domains: Math, Code, Science, Logic, Simulation, and Tabular, each with corresponding verifiers.We build GURU via a careful data-curation pipeline, including sourcing, deduplication, reward design, and domain-specific and difficulty-based filtering.With GURU, we present a systematic investigation of cross-domain RL generalization, and reveal several key aspects affecting crossdomain transferability.We further train two models GURU-7B and GURU-32B purely with RL on our curated data and observe largely improved performance over leading open RL reasoning model baselines, with gains of 7.3% and 7.8% respectively on an extensive 17-task, six-domain evaluation suite.We are releasing our dataset, code, and evaluation suite to the community, aiming to support further research and development of more general RL-enhanced reasoning models.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Cheng, J., Hao, S., Liu, T., Zhou, F., Xie, Y., Yao, F., Bian, Y., Dey, N., Zhuang, Y., Zha, Y., Gu, Y., Zhou, K., Wang, Y., Li, Y., Fan, R., She, J., Gao, C., Saparov, A., Killian, T. W., . . . Hu, Z. (2025). Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective. neural information processing systems, 148885–148905. https://doi.org/10.52202/085713-4479
MLA 9
Cheng, Jorge (Zhoujun), et al. “Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective.” neural information processing systems, 2025, pp. 148885–148905. https://doi.org/10.52202/085713-4479.
Chicago
Cheng, Jorge (Zhoujun), Shibo Hao, Tianyang Liu, Fan Zhou, Yutao Xie, Feng Yao, Yuexin Bian, et al. 2025. “Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective.” neural information processing systems: 148885–148905. https://doi.org/10.52202/085713-4479.
Harvard
Cheng, J. et al. (2025) ‘Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective’, neural information processing systems, pp. 148885–148905. doi:10.52202/085713-4479.
IEEE
J. Cheng et al., “Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective,” neural information processing systems, pp. 148885–148905, 2025, doi: 10.52202/085713-4479.
BibTeX
@inproceedings{cheng2025revisiting,
title = {{Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective}},
author = {Cheng, Jorge (Zhoujun) and Hao, Shibo and Liu, Tianyang and Zhou, Fan and Xie, Yutao and Yao, Feng and Bian, Yuexin and Dey, Nolan and Zhuang, Yonghao and Zha, Yuheng and Gu, Yi and Zhou, Kun and Wang, Yuqi and Li, Yuan and Fan, Richard and She, Jianshu and Gao, Chengqian and Saparov, Abulhair and Killian, Taylor W. and Li, Haonan and Yurochkin, Mikhail and Xing, Eric and Liu, Zhengzhong and Hu, Zhiting},
booktitle = {neural information processing systems},
year = {2025},
pages = {148885--148905},
doi = {10.52202/085713-4479},
url = {https://doi.org/10.52202/085713-4479}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- large language model reasoning
- reinforcement learning for reasoning
- cross-domain transferability
- reasoning datasets
- reward function design
- data curation
- mathematical reasoning
- code reasoning
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?
Cheng, J., Hao, S., Liu, T., Zhou, F., Xie, Y., Yao, F., Bian, Y., Dey, N., Zhuang, Y., Zha, Y., Gu, Y., Zhou, K., Wang, Y., Li, Y., Fan, R., She, J., Gao, C., Saparov, A., Killian, T. W., . . . Hu, Z. (2025). Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective. neural information processing systems, 148885–148905. https://doi.org/10.52202/085713-4479
How many times has this paper been cited?
0 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 neural information processing systems.
Who wrote this paper?
Jorge (Zhoujun) Cheng, Shibo Hao, Tianyang Liu, Fan Zhou, Yutao Xie, Feng Yao, Yuexin Bian, Nolan Dey, Yonghao Zhuang, Yuheng Zha, Yi Gu, Kun Zhou and 12 more.
What is the DOI of this paper?
10.52202/085713-4479. The permanent link is https://doi.org/10.52202/085713-4479.
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.