Preprint · 2026 · Open access

Can a Lightweight Automated AI Pipeline Solve Research-Level Mathematical Problems?

Lve Meng, Weilong Zhao, Yanzhi Zhang, Haoxiang Guan, Jiyan He

arXiv (Cornell University) · Published 14 February 2026 · DOI 10.48550/arxiv.2602.13695

Open PDFView at the publisherCite this paper

In brief

“Can a Lightweight Automated AI Pipeline Solve Research-Level Mathematical Problems?” is a 2026 preprint by Lve Meng and 4 co-authors, published in arXiv (Cornell University). OpenAlex counts 0 citations as of 21 November 2026. It is open access under a CC BY-NC-SA licence: the full text is free to read at arXiv (Cornell University).

Citations
0
References
8
Authors
5

Abstract

Large language models (LLMs) have recently achieved remarkable success in generating rigorous mathematical proofs, with "AI for Math" emerging as a vibrant field of research (Ju et al., 2026). While these models have mastered competition-level benchmarks like the International Mathematical Olympiad (Huang et al., 2025; Duan et al., 2025) and show promise in research applications through auto-formalization (Wang et al., 2025), their deployment via lightweight, natural-language pipelines for research problems remains underexplored. In this work, we demonstrate that next-generation models (e.g., Gemini 3 Pro, GPT-5.2 Pro), when integrated into a streamlined automated pipeline optimized for citation-based verification, can solve sophisticated research-grade problems. We evaluate our pipeline on two novel datasets: (1) the ICCM (2025) problem sets (comparable to the S.-T. Yau College Student Mathematics Contest) proposed by leading mathematicians (Shanghai Math Challenge, 2026), and (2) the "First Proof" problem set (Abouzaid et al., 2026), consisting of previously unpublished research questions. Our pipeline generated candidate proofs for all problems in the first two ICCM sets and the "First Proof" set. The solutions for the first two ICCM sets and Problem 4 of the "First Proof" set have been fully verified by our team. All generated proofs have been submitted to the official organization, and our generated results are publicly available at https://github.com/ml1301215/question_sets-test_results. We have open-sourced the code and developed a user-friendly UI for this workflow, accessible at https://github.com/ml1301215/research-math-assistant.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Meng, L., Zhao, W., Zhang, Y., Guan, H., & He, J. (2026). Can a Lightweight Automated AI Pipeline Solve Research-Level Mathematical Problems? arXiv (Cornell University). https://doi.org/10.48550/arxiv.2602.13695

MLA 9

Meng, Lve, et al. “Can a Lightweight Automated AI Pipeline Solve Research-Level Mathematical Problems?” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2602.13695.

Chicago

Meng, Lve, Weilong Zhao, Yanzhi Zhang, Haoxiang Guan, and Jiyan He. 2026. “Can a Lightweight Automated AI Pipeline Solve Research-Level Mathematical Problems?” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2602.13695.

Harvard

Meng, L. et al. (2026) ‘Can a Lightweight Automated AI Pipeline Solve Research-Level Mathematical Problems?’, arXiv (Cornell University). doi:10.48550/arxiv.2602.13695.

IEEE

L. Meng, W. Zhao, Y. Zhang, H. Guan, and J. He, “Can a Lightweight Automated AI Pipeline Solve Research-Level Mathematical Problems?,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2602.13695.

BibTeX

@misc{meng2026lightweight,
  title     = {{Can a Lightweight Automated AI Pipeline Solve Research-Level Mathematical Problems?}},
  author    = {Meng, Lve and Zhao, Weilong and Zhang, Yanzhi and Guan, Haoxiang and He, Jiyan},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2602.13695},
  url       = {https://doi.org/10.48550/arxiv.2602.13695}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Computational Theory and Mathematics › Mathematics, Computing, and Information Processing

  • large language models
  • automated proof checking
  • Gemini 3 Pro

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Meng, L., Zhao, W., Zhang, Y., Guan, H., & He, J. (2026). Can a Lightweight Automated AI Pipeline Solve Research-Level Mathematical Problems? arXiv (Cornell University). https://doi.org/10.48550/arxiv.2602.13695

How many times has this paper been cited?

0 times, according to OpenAlex on 21 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?

Lve Meng, Weilong Zhao, Yanzhi Zhang, Haoxiang Guan, Jiyan He.

What is the DOI of this paper?

10.48550/arxiv.2602.13695, permanently at https://doi.org/10.48550/arxiv.2602.13695. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 21 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.