Autonomous disproofs of the sum-product conjecture over mathbb R with GPT-5.5 Pro
Not on the map. Why?
Abstract (arXiv)
OpenAI's recent disproof of the ErdHos unit distance conjecture marked a milestone for AI in mathematics. It also inspired another breakthrough: a human disproof of the ErdHos--Szemer'edi sum-product conjecture over mathbb 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 mathbb 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 Lp-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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 0 of its 10 references that are in the map. First posted on arXiv 9 Jul 2026.
Builds on
0 of 10 references.
No references here yet.
Built on by
Citing papers per year: 2026: 1.
1 paper.
- 2026Learning to Discover Interesting Mathematicscited by 0
- 2026Learning to Discover Interesting Mathematics23 Sep 2026
Similar, not cited
Close in wording, no citation either way
- 2026Advancing Mathematics Research with AI-Driven Formal Proof Search
- 2026Iteris: Agentic Research Loops for Computational Mathematics
- 2026MathAdv: What Theorem Provers Know, Reason, Formalize, and Generalize
- 2024MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs
- 2025STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving
- 2026Towards Autonomous Mathematics Research
- 2026RMA: an Agentic System for Research-Level Mathematical Problems
- 2026Measuring Progress in Reasoning Toward Mathematical Discovery with Automatic Verification