Preprint · 2026 · Open access

Mathematical Scientific Discovery Using Large Language Models: A Systematic Literature Review

Vinita Gangaram Jansari, Carlos Toxtli, Michael Burr, Austin LaHue, Ben Nye, Luis David García Puente

Research Square · Published 3 August 2026 · DOI 10.21203/rs.3.rs-10387804/v1

Open PDFView at the publisherCite this paper

In brief

“Mathematical Scientific Discovery Using Large Language Models: A Systematic Literature Review” is a 2026 preprint by Vinita Gangaram Jansari and 5 co-authors, published in Research Square. OpenAlex counts 0 citations as of 18 November 2026. It is open access under a CC BY licence: the full text is free to read at Research Square.

Citations
0
References
61
Authors
6

Abstract

The intersection of large language models (LLMs) and mathematical discovery represents a rapidly evolving frontier in artificial intelligence research. This systematic literature review, conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines, examines the current state of research on using LLMs for generating new mathematical knowledge, including conjectures, theorems, lemmas, axioms, and counterexamples. From an initial pool of 63 records published through December 31, 2025, we identified 32 studies that met our inclusion criteria after rigorous screening. Our analysis reveals seven distinct technical paradigms: evolutionary search methods, reinforcement learning (RL) approaches, self-play and expert iteration, neuro-symbolic hybrid systems, in-context learning pipelines, specialized pretraining objectives, and equation discovery techniques. We amalgamate findings across formal verification systems (including Lean, Isabelle, PVS, and Metamath), along with datasets, evaluation metrics, and architectural choices. Our review identifies that evolutionary approaches combined with formal verification have achieved the most significant mathematical discoveries, including improvements to Strassen's matrix multiplication algorithm and solutions to open problems in extremal combinatorics. We provide a technical taxonomy to guide practitioners in designing novel architectures for mathematical discovery, highlighting both proven strategies and open challenges in this emerging field.

Cite this paper

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

APA 7

Jansari, V. G., Toxtli, C., Burr, M., LaHue, A., Nye, B., & Puente, L. D. G. (2026). Mathematical Scientific Discovery Using Large Language Models: A Systematic Literature Review. Research Square. https://doi.org/10.21203/rs.3.rs-10387804/v1

MLA 9

Jansari, Vinita Gangaram, et al. “Mathematical Scientific Discovery Using Large Language Models: A Systematic Literature Review.” Research Square, 2026. https://doi.org/10.21203/rs.3.rs-10387804/v1.

Chicago

Jansari, Vinita Gangaram, Carlos Toxtli, Michael Burr, Austin LaHue, Ben Nye, and Luis David García Puente. 2026. “Mathematical Scientific Discovery Using Large Language Models: A Systematic Literature Review.” Research Square. https://doi.org/10.21203/rs.3.rs-10387804/v1.

Harvard

Jansari, V. G. et al. (2026) ‘Mathematical Scientific Discovery Using Large Language Models: A Systematic Literature Review’, Research Square. doi:10.21203/rs.3.rs-10387804/v1.

IEEE

V. G. Jansari, C. Toxtli, M. Burr, A. LaHue, B. Nye, and L. D. G. Puente, “Mathematical Scientific Discovery Using Large Language Models: A Systematic Literature Review,” Research Square, 2026, doi: 10.21203/rs.3.rs-10387804/v1.

BibTeX

@misc{jansari2026mathematical,
  title     = {{Mathematical Scientific Discovery Using Large Language Models: A Systematic Literature Review}},
  author    = {Jansari, Vinita Gangaram and Toxtli, Carlos and Burr, Michael and LaHue, Austin and Nye, Ben and Puente, Luis David García},
  howpublished = {Research Square},
  year      = {2026},
  doi       = {10.21203/rs.3.rs-10387804/v1},
  url       = {https://doi.org/10.21203/rs.3.rs-10387804/v1}
}

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

  • large language models
  • mathematical discovery
  • automated theorem proving
  • conjecture generation
  • formal verification
  • evolutionary search
  • reinforcement learning
  • in-context learning

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?

Jansari, V. G., Toxtli, C., Burr, M., LaHue, A., Nye, B., & Puente, L. D. G. (2026). Mathematical Scientific Discovery Using Large Language Models: A Systematic Literature Review. Research Square. https://doi.org/10.21203/rs.3.rs-10387804/v1

How many times has this paper been cited?

0 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 Research Square: sign in and open the PDF from this page.

Who wrote this paper?

Vinita Gangaram Jansari, Carlos Toxtli, Michael Burr, Austin LaHue, Ben Nye, Luis David García Puente.

What is the DOI of this paper?

10.21203/rs.3.rs-10387804/v1, permanently at https://doi.org/10.21203/rs.3.rs-10387804/v1. 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.