[Submitted on 7 Oct 2026 (v1), last revised 9 Oct 2026 (this version, v2)]
Abstract:Large language models are increasingly contributing to mathematical research, where progress often depends on efficient proof search, incremental improvements and careful verification. We describe Bolzano, a multi-agent open-source system that uses parallel prover agents with a verifier agent and maintains a human-readable research state. Initial manual use on expert-selected problems yielded 8 results whose proofs were checked by domain experts. Motivated by these case studies, we ran Bolzano without problem-specific human guidance on about 3,800 open problems extracted from four sets of papers, solving about 200 open problems. One experiment used papers accepted to STOC 2026, a top conference in theoretical computer science. There, we answered four questions raised in the papers, as confirmed by their authors.
Submission history
From: Matěj Kripner [view email]
[v1] Wed, 7 Oct 2026 09:52:46 UTC (13 KB)
[v2] Fri, 9 Oct 2026 13:27:33 UTC (13 KB)