Bolzano: Case Studies in LLM-Assisted Mathematical Research

April 18, 2026 ยท Grace Period ยท + Add venue

โณ Grace Period
This paper is less than 90 days old. We give authors time to release their code before passing judgment.
Authors Jan Grebรญk, Pavel Hubรกฤek, Martin Kouteckรฝ, Matฤ›j Kripner, Vรกclav Rozhoลˆ, Robert ล รกmal, Adriรกn Zรกmeฤnรญk arXiv ID 2604.16989 Category cs.CL: Computation & Language Cross-listed cs.AI, cs.LG, cs.LO Citations 0
Abstract
We report new results on six problems in mathematics and theoretical computer science, produced with the assistance of Bolzano, an open-source multi-agent LLM system. Bolzano orchestrates rounds of interaction between parallel prover agents and a verifier agent while maintaining a persistent knowledge base that is carried across rounds. Classified using the significance-autonomy taxonomy of Feng et al., four of the six results reach the level of publishable research, and three of the six were produced essentially autonomously by Bolzano. Our results provide evidence that LLMs can contribute meaningfully to mathematical research, complementing recent reports by Bubeck et al., Woodruff et al., and others.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Computation & Language

๐ŸŒ… ๐ŸŒ… Old Age

Attention Is All You Need

Ashish Vaswani, Noam Shazeer, ... (+6 more)

cs.CL ๐Ÿ› NeurIPS ๐Ÿ“š 166.0K cites 9 years ago