Conference paper · 2025 · Open access
General-Reasoner: Advancing LLM Reasoning Across All Domains
neural information processing systems, 63009–63031 · Published 1 January 2025 · DOI 10.52202/085713-1893
In brief
“General-Reasoner: Advancing LLM Reasoning Across All Domains” is a 2025 conference paper by Xueguang Ma and 5 co-authors, published in neural information processing systems. OpenAlex counts 109 citations as of 15 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 109
- Most cited in
- 2026 (67)
- Field-weighted impact
- 38.03
- References
- 20
- Authors
- 6
Abstract
Reinforcement learning (RL) has recently demonstrated strong potential in enhancing the reasoning capabilities of large language models (LLMs). Particularly, the "Zero" reinforcement learning introduced by Deepseek-R1-Zero, enables direct RL training of base LLMs without relying on an intermediate supervised fine-tuning stage. Despite these advancements, current works for LLM reasoning mainly focus on mathematical and coding domains, largely due to data abundance and the ease of answer verification. This limits the applicability and generalization of such models to broader domains, where questions often have diverse answer representations, and data is more scarce. In this paper, we propose General-Reasoner, a novel training paradigm designed to enhance LLM reasoning capabilities across diverse domains. Our key contributions include: (1) constructing a large-scale, high-quality dataset of questions with verifiable answers curated by web crawling, covering a wide range of disciplines; and (2) developing a generative model-based answer verifier, which replaces traditional rule-based verification with the capability of chain-of-thought and context-awareness. We train a series of models and evaluate them on a wide range of datasets covering wide domains like physics, chemistry, finance, electronics etc. Our comprehensive evaluation across these 12 benchmarks (e.g. MMLU-Pro, GPQA, SuperGPQA, TheoremQA, BBEH and MATH AMC) demonstrates that General-Reasoner outperforms existing baseline methods, achieving robust and generalizable reasoning performance while maintaining superior effectiveness in mathematical reasoning tasks.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Ma, X., Liu, Q., Jiang, D., ZHANG, G., Ma, Z., & Chen, W. (2025). General-Reasoner: Advancing LLM Reasoning Across All Domains. neural information processing systems, 63009–63031. https://doi.org/10.52202/085713-1893
MLA 9
Ma, Xueguang, et al. “General-Reasoner: Advancing LLM Reasoning Across All Domains.” neural information processing systems, 2025, pp. 63009–63031. https://doi.org/10.52202/085713-1893.
Chicago
Ma, Xueguang, Qian Liu, Dongfu Jiang, Ge ZHANG, Zejun Ma, and Wenhu Chen. 2025. “General-Reasoner: Advancing LLM Reasoning Across All Domains.” neural information processing systems: 63009–63031. https://doi.org/10.52202/085713-1893.
Harvard
Ma, X. et al. (2025) ‘General-Reasoner: Advancing LLM Reasoning Across All Domains’, neural information processing systems, pp. 63009–63031. doi:10.52202/085713-1893.
IEEE
X. Ma, Q. Liu, D. Jiang, G. ZHANG, Z. Ma, and W. Chen, “General-Reasoner: Advancing LLM Reasoning Across All Domains,” neural information processing systems, pp. 63009–63031, 2025, doi: 10.52202/085713-1893.
BibTeX
@inproceedings{ma2025general,
title = {{General-Reasoner: Advancing LLM Reasoning Across All Domains}},
author = {Ma, Xueguang and Liu, Qian and Jiang, Dongfu and ZHANG, Ge and Ma, Zejun and Chen, Wenhu},
booktitle = {neural information processing systems},
year = {2025},
pages = {63009--63031},
doi = {10.52202/085713-1893},
url = {https://doi.org/10.52202/085713-1893}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2023 | 1 | |
| 2025 | 41 | |
| 2026 | 67 |
Its field-weighted citation impact is 38.03: it has been cited 38.03 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 › Artificial Intelligence › Topic Modeling
- LLM reasoning
- large language models
- cross-domain reasoning
- answer verification
- chain-of-thought
- question answering dataset
- physics reasoning
- financial 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?
Ma, X., Liu, Q., Jiang, D., ZHANG, G., Ma, Z., & Chen, W. (2025). General-Reasoner: Advancing LLM Reasoning Across All Domains. neural information processing systems, 63009–63031. https://doi.org/10.52202/085713-1893
How many times has this paper been cited?
109 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?
Xueguang Ma, Qian Liu, Dongfu Jiang, Ge ZHANG, Zejun Ma, Wenhu Chen.
What is the DOI of this paper?
10.52202/085713-1893. The permanent link is https://doi.org/10.52202/085713-1893.
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.