🤖 AI Summary
This work investigates the capacity of artificial intelligence to address open problems in pure mathematics, with a focus on Banach space theory. By integrating large language models for conjecture and proof generation, automated literature mining, formal verification, and a human–AI collaborative reasoning framework, the study achieves the first instance of AI autonomously proposing verifiable new theorems in advanced pure mathematics. The approach yielded five novel mathematical results, all rigorously validated by human experts. These findings not only demonstrate the practical potential of large language models in abstract mathematical research but also establish a new paradigm for AI–human collaboration in mathematical discovery.
📝 Abstract
We investigate the capacity of current language models to contribute to mathematical research. In Banach space theory, AI systems generated key ideas and proofs for five new results, which were then verified and refined by humans. We also developed an automated system that searches the literature for open problems and attempts solutions at scale. Our results show both the potential of language models for mathematical discovery and the continuing importance of expert verification.