Preprint · 2026 · Open access
Towards Autonomous Mathematics Research
arXiv (Cornell University) · Published 10 February 2026 · DOI 10.48550/arxiv.2602.10177
In brief
“Towards Autonomous Mathematics Research” is a 2026 preprint by Tony Feng and 27 co-authors, published in arXiv (Cornell University). OpenAlex counts 100 citations as of 20 November 2026. It is open access under a CC BY-NC-ND licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 100
- Most cited in
- 2026 (100)
- References
- 38
- Authors
- 28
Abstract
Recent advances in foundational models have yielded reasoning systems capable of achieving a gold-medal standard at the International Mathematical Olympiad. The transition from competition-level problem-solving to professional research, however, requires navigating vast literature and constructing long-horizon proofs. In this work, we introduce Aletheia, a math research agent that iteratively generates, verifies, and revises solutions end-to-end in natural language. Specifically, Aletheia is powered by an advanced version of Gemini Deep Think for challenging reasoning problems, a novel inference-time scaling law that extends beyond Olympiad-level problems, and intensive tool use to navigate the complexities of mathematical research. We demonstrate the capability of Aletheia from Olympiad problems to PhD-level exercises and most notably, through several distinct milestones in AI-assisted mathematics research: (a) a research paper (Feng26) generated by AI without any human intervention in calculating certain structure constants in arithmetic geometry called eigenweights; (b) a research paper (LeeSeo26) demonstrating human-AI collaboration in proving bounds on systems of interacting particles called independent sets; and (c) an extensive semi-autonomous evaluation (Feng et al., 2026a) of 700 open problems on Bloom's Erdos Conjectures database, including autonomous solutions to four open questions. In order to help the public better understand the developments pertaining to AI and mathematics, we suggest quantifying standard levels of autonomy and novelty of AI-assisted results, as well as propose a novel concept of human-AI interaction cards for transparency. We conclude with reflections on human-AI collaboration in mathematics and share all prompts as well as model outputs at https://github.com/google-deepmind/superhuman/tree/main/aletheia.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Feng, T., Trinh, T., Bingham, G., Hwang, D., Chervonyi, Y., Jung, J., Lee, J., Pagano, C., Kim, S.-H., Pasqualotto, F., Gukov, S., Lee, J. N., Kim, J., Hou, K., Ghiasi, G., Tay, Y., Li, Y., Kuang, C., Liu, Y., . . . Luong, M.-T. (2026). Towards Autonomous Mathematics Research. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2602.10177
MLA 9
Feng, Tony, et al. “Towards Autonomous Mathematics Research.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2602.10177.
Chicago
Feng, Tony, Trieu Trinh, Garrett Bingham, Dawsen Hwang, Yuri Chervonyi, Junehyuk Jung, Joonkyung Lee, et al. 2026. “Towards Autonomous Mathematics Research.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2602.10177.
Harvard
Feng, T. et al. (2026) ‘Towards Autonomous Mathematics Research’, arXiv (Cornell University). doi:10.48550/arxiv.2602.10177.
IEEE
T. Feng et al., “Towards Autonomous Mathematics Research,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2602.10177.
BibTeX
@misc{feng2026towards,
title = {{Towards Autonomous Mathematics Research}},
author = {Feng, Tony and Trinh, Trieu and Bingham, Garrett and Hwang, Dawsen and Chervonyi, Yuri and Jung, Junehyuk and Lee, Joonkyung and Pagano, Carlo and Kim, Sang-hyun and Pasqualotto, Federico and Gukov, Sergei and Lee, Jonathan N. and Kim, Junsu and Hou, Kaiying and Ghiasi, Golnaz and Tay, Yi and Li, Yaguang and Kuang, Chenkai and Liu, Yuan and Hanzhao and Liu, Evan Zheran and Nayakanti, Nigamaa and Yang, Xiaomeng and Cheng, Heng-Tze and Hassabis, Demis and Kavukcuoglu, Koray and Le, Quoc Viet and Luong, Minh-Thang},
howpublished = {arXiv (Cornell University)},
year = {2026},
doi = {10.48550/arxiv.2602.10177},
url = {https://doi.org/10.48550/arxiv.2602.10177}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- aletheia
- proof verification
- human-AI collaboration
- independent sets
- Erdős conjecture
- open problems
- autonomy levels
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?
Feng, T., Trinh, T., Bingham, G., Hwang, D., Chervonyi, Y., Jung, J., Lee, J., Pagano, C., Kim, S.-H., Pasqualotto, F., Gukov, S., Lee, J. N., Kim, J., Hou, K., Ghiasi, G., Tay, Y., Li, Y., Kuang, C., Liu, Y., . . . Luong, M.-T. (2026). Towards Autonomous Mathematics Research. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2602.10177
How many times has this paper been cited?
100 times, according to OpenAlex on 20 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?
Tony Feng, Trieu Trinh, Garrett Bingham, Dawsen Hwang, Yuri Chervonyi, Junehyuk Jung, Joonkyung Lee, Carlo Pagano, Sang-hyun Kim, Federico Pasqualotto, Sergei Gukov, Jonathan N. Lee and 16 more.
What is the DOI of this paper?
10.48550/arxiv.2602.10177, permanently at https://doi.org/10.48550/arxiv.2602.10177. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 20 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.