Preprint · 2025 · Open access

Even with AI, Bijection Discovery is Still Hard: The Opportunities and Challenges of OpenEvolve for Novel Bijection Construction

Davis Brown, Jesse He, Helen Jenne, Henry Kvinge, Vargas, Max

arXiv (Cornell University) · Published 26 November 2025 · DOI 10.48550/arxiv.2511.20987

Open PDFView at the publisherCite this paper

In brief

“Even with AI, Bijection Discovery is Still Hard: The Opportunities and Challenges of OpenEvolve for Novel Bijection Construction” is a 2025 preprint by Davis Brown and 4 co-authors, published in arXiv (Cornell University). OpenAlex counts 6 citations as of 18 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
6
Most cited in
2026 (6)
References
17
Authors
5

Abstract

Evolutionary program synthesis systems such as AlphaEvolve, OpenEvolve, and ShinkaEvolve offer a new approach to AI-assisted mathematical discovery. These systems utilize teams of large language models (LLMs) to generate candidate solutions to a problem as human readable code. These candidate solutions are then 'evolved' with the goal of improving them beyond what an LLM can produce in a single shot. While existing mathematical applications have mostly focused on problems of establishing bounds (e.g., sphere packing), the program synthesis approach is well suited to any problem where the solution takes the form of an explicit construction. With this in mind, in this paper we explore the use of OpenEvolve for combinatorial bijection discovery. We describe the results of applying OpenEvolve to three bijection construction problems involving Dyck paths, two of which are known and one of which is open. We find that while systems like OpenEvolve show promise as a valuable tool for combinatorialists, the problem of finding novel, research-level bijections remains a challenging task for current frontier systems, reinforcing the need for human mathematicians in the loop. We describe some lessons learned for others in the field interested in exploring the use of these systems.

Cite this paper

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

APA 7

Brown, D., He, J., Jenne, H., Kvinge, H., & Max, V. (2025). Even with AI, Bijection Discovery is Still Hard: The Opportunities and Challenges of OpenEvolve for Novel Bijection Construction. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2511.20987

MLA 9

Brown, Davis, et al. “Even with AI, Bijection Discovery is Still Hard: The Opportunities and Challenges of OpenEvolve for Novel Bijection Construction.” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2511.20987.

Chicago

Brown, Davis, Jesse He, Helen Jenne, Henry Kvinge, and Vargas, Max. 2025. “Even with AI, Bijection Discovery is Still Hard: The Opportunities and Challenges of OpenEvolve for Novel Bijection Construction.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2511.20987.

Harvard

Brown, D. et al. (2025) ‘Even with AI, Bijection Discovery is Still Hard: The Opportunities and Challenges of OpenEvolve for Novel Bijection Construction’, arXiv (Cornell University). doi:10.48550/arxiv.2511.20987.

IEEE

D. Brown, J. He, H. Jenne, H. Kvinge, and V. Max, “Even with AI, Bijection Discovery is Still Hard: The Opportunities and Challenges of OpenEvolve for Novel Bijection Construction,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2511.20987.

BibTeX

@misc{brown2025even,
  title     = {{Even with AI, Bijection Discovery is Still Hard: The Opportunities and Challenges of OpenEvolve for Novel Bijection Construction}},
  author    = {Brown, Davis and He, Jesse and Jenne, Helen and Kvinge, Henry and Max, Vargas,},
  howpublished = {arXiv (Cornell University)},
  year      = {2025},
  doi       = {10.48550/arxiv.2511.20987},
  url       = {https://doi.org/10.48550/arxiv.2511.20987}
}

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

  • combinatorial bijections
  • Dyck paths
  • large language models
  • explicit constructions
  • human-in-the-loop

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?

Brown, D., He, J., Jenne, H., Kvinge, H., & Max, V. (2025). Even with AI, Bijection Discovery is Still Hard: The Opportunities and Challenges of OpenEvolve for Novel Bijection Construction. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2511.20987

How many times has this paper been cited?

6 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?

Davis Brown, Jesse He, Helen Jenne, Henry Kvinge, Vargas, Max.

What is the DOI of this paper?

10.48550/arxiv.2511.20987, permanently at https://doi.org/10.48550/arxiv.2511.20987. 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.