Top artificial intelligence systems now ace many textbook-style math questions, yet they still fall apart on genuinely new problems. The gap between polished performance on familiar benchmarks and ...

The second batch of “First Proof” problems is meant to evaluate AI’s usefulness for research-level math. The best model got ...

Word problems are often described as “math stories” and can put complex mathematical operations into a more approachable form for students. But students often struggle when they see a combination of ...

Clarification: This story has been updated to clarify how University of Colorado researchers handle their data collection. A student digs into a math problem that references his favorite superhero, ...