In plain words: A set of 29 open problems asks for simple combinatorial rules explaining given polynomial coefficients or identities, with tools to test answers and block shortcuts. Frontier AI systems proposed solutions to several, raising questions about whether to release such discoveries and how to verify the proofs.
Abstract · AI Discovery in Combinatorics: From Problems to Solutions and Back to Bigger Problems
We introduce $qt$Bench, a benchmark of 29 open problems in algebraic combinatorics. These problems ask for a simple combinatorial algorithm that explains given polynomial coefficients or identities. To help AI agents search for such algorithms, we provide a scaffold for playing with combinatorial objects, countering cheating attempts, and testing candidate solutions. To explore how far frontier AI systems can go on these problems, we collaborated with OpenAI, whose researchers obtained proposed solutions to several of them. This highlights bigger meta-problems: is AI discovery at scale ethical? How should these results be released? How should proof digestion be organized? We discuss these questions and give our views.
Eugenio Cainelli, Lorenzo Luccioli, Alessandro Iraci, Giovanni Paolini
arXiv:2610.16555 · cs.AI, cs.LG, math.CO · submitted Oct 12, 2026
abstract · pdf · 15 pages