Preprint · 2026 · Open access
Code2Math: Can Your Code Agent Evolve Math Problems Through Exploration?
arXiv (Cornell University) · Published 3 March 2026 · DOI 10.48550/arxiv.2603.03202
In brief
“Code2Math: Can Your Code Agent Evolve Math Problems Through Exploration?” is a 2026 preprint by Dadi Guo and 13 co-authors, published in arXiv (Cornell University). OpenAlex counts 3 citations as of 18 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 3
- Most cited in
- 2026 (3)
- References
- 42
- Authors
- 14
Abstract
As large language models (LLMs) advance their mathematical capabilities toward the IMO and research level, the scarcity of challenging, high-quality problems has become a significant bottleneck for training, evaluation and self-evolution of LLMs. Simultaneously, recent code agents have demonstrated sophisticated skills in agentic coding and reasoning, suggesting that code execution can serve as a scalable environment for mathematical experimentation. In this paper, we investigate the potential of code agents to autonomously evolve existing math problems into more complex variations. We introduce a multi-agent framework designed to perform problem evolution while validating the solvability and increased difficulty of the generated problems. Our experiments demonstrate that, given sufficient test-time exploration, code agents can synthesize new, solvable problems that are structurally distinct from and more challenging than the originals. This work provides empirical evidence that code-driven agents can serve as a viable mechanism for synthesizing high-difficulty mathematical reasoning problems within scalable computational environments. Code and data is available at https://github.com/TarferSoul/Code2Math.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Guo, D., Xie, Y., Liu, Q., Huang, W., Liu, J., Fan, Z., Ren, Q., Shao, S., Zhou, T., Fung, Y. R., Su, W., Yang, Y., Liu, D., & Fung, Y. R. (2026). Code2Math: Can Your Code Agent Evolve Math Problems Through Exploration? arXiv (Cornell University). https://doi.org/10.48550/arxiv.2603.03202
MLA 9
Guo, Dadi, et al. “Code2Math: Can Your Code Agent Evolve Math Problems Through Exploration?” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2603.03202.
Chicago
Guo, Dadi, Yuejin Xie, Qingyu Liu, Weixian Huang, Jiayu Liu, Zhiyuan Fan, Qihan Ren, et al. 2026. “Code2Math: Can Your Code Agent Evolve Math Problems Through Exploration?” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2603.03202.
Harvard
Guo, D. et al. (2026) ‘Code2Math: Can Your Code Agent Evolve Math Problems Through Exploration?’, arXiv (Cornell University). doi:10.48550/arxiv.2603.03202.
IEEE
D. Guo et al., “Code2Math: Can Your Code Agent Evolve Math Problems Through Exploration?,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2603.03202.
BibTeX
@misc{guo2026code,
title = {{Code2Math: Can Your Code Agent Evolve Math Problems Through Exploration?}},
author = {Guo, Dadi and Xie, Yuejin and Liu, Qingyu and Huang, Weixian and Liu, Jiayu and Fan, Zhiyuan and Ren, Qihan and Shao, Shuai and Zhou, Tianyi and Fung, Yi R. and Su, Wenze and Yang, Yujiu and Liu, Dongrui and Fung, Yi R.},
howpublished = {arXiv (Cornell University)},
year = {2026},
doi = {10.48550/arxiv.2603.03202},
url = {https://doi.org/10.48550/arxiv.2603.03202}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Evolutionary Algorithms and Applications
- coding agents
- multi-agent systems
- large language models
- mathematical reasoning
- problem difficulty
- program execution
- agentic coding
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?
Guo, D., Xie, Y., Liu, Q., Huang, W., Liu, J., Fan, Z., Ren, Q., Shao, S., Zhou, T., Fung, Y. R., Su, W., Yang, Y., Liu, D., & Fung, Y. R. (2026). Code2Math: Can Your Code Agent Evolve Math Problems Through Exploration? arXiv (Cornell University). https://doi.org/10.48550/arxiv.2603.03202
How many times has this paper been cited?
3 times, according to OpenAlex on 18 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 at arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Dadi Guo, Yuejin Xie, Qingyu Liu, Weixian Huang, Jiayu Liu, Zhiyuan Fan, Qihan Ren, Shuai Shao, Tianyi Zhou, Yi R. Fung, Wenze Su, Yujiu Yang and 2 more.
What is the DOI of this paper?
10.48550/arxiv.2603.03202, permanently at https://doi.org/10.48550/arxiv.2603.03202. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.