Tag
This paper introduces Cartograph, a verification layer for AI scientists that couples subspace experiment steering, ambiguity resolution, and library inadequacy detection. The framework outperforms baselines in autonomous discovery testbeds and retrospectively flags inconclusive claims in the A-Lab materials system.
This paper introduces GRAFT-ATHENA, a self-improving agentic framework that autonomously discovers and evolves numerical algorithms for scientific problems. It demonstrates near-machine-precision accuracy on physics-informed machine learning benchmarks and successfully tackles complex engineering challenges.
An OpenAI model has autonomously solved the planar unit distance problem, a famous open question in mathematics posed by Paul Erdős in 1946, by discovering a new family of constructions that outperform square grids. This marks the first time AI has autonomously proven a prominent open problem in mathematics.