Bolzano: Case Studies in LLM-Assisted Mathematical Research

ArXi:2604.16989v1 Announce Type: cross 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, four of the six results reach the level of publishable research, and three of the six were produced essentially autonomously by Bolzano.