Abstract
OpenAI's recent disproof of the Erdős unit distance conjecture marked a milestone for AI in mathematics. It also inspired another breakthrough: a human disproof of the Erdős–Szemerédi sum-product conjecture over $\mathbf{R}$.
In this paper, we present a simple agent built on GPT-5.5 Pro. Using a problem-agnostic, three-stage prompting pipeline — proof-plan proposal, proof construction, and review — the agent autonomously generated correct proofs that the sum-product conjecture is false over $\mathbf{R}$ in 7 of 8 independent trials; in the remaining trial, it identified an unresolved gap in its argument.
The seven proofs are diverse: some are close to existing unit-based constructions, while others avoid units by using $L^p$-type regions of algebraic integers. The system used an average of 132.4k reasoning tokens per trial. We release the code, intermediate outputs, and generated proofs, providing a reproducible, data-contamination-free case study in autonomous proof generation.
Blogger's Review: This paper showcases the immense potential of AI in generating mathematical proofs, particularly how GPT-5.5 Pro effectively identifies and resolves complex mathematical problems. It not only provides new tools for mathematical research but also prompts deep reflections on the relationship between AI and mathematics.