Artificial intelligence systems may be good at generating text, recognizing images, and even solving basic math problems—but when it comes to advanced mathematical reasoning, they are hitting a wall.

From high school math modeling challenges to formal theorem-proving competitions, large language models (LLMs) are stepping into the competitive math arena. New datasets, benchmarks, and governance ...

Every year, the countries competing in the International Mathematical Olympiad arrive with a booklet of their best, most ...