← Back
Computation

Proving Math Theorems is Challenging for Both Humans and AI

Both human mathematicians and current AI systems struggle with proving complex math theorems. Enhancing theorem proving through interactive and automated methods could push the boundaries of mathematical reasoning.

Foundational Capabilities (1)

Reinforcement Learning from Interactive Theorem Prover Feedback

Close the loop between AI and human-guided interactive theorem provers by using reinforcement learning to refine proofs based on feedback from proof assistants.
  • Harmonic
    Company
  • LEAN: Developing a dependently typed programming language and proof assistant
    FRO
  • AI for Math Fund
    Funding Program
  • Future Program: Exponentiating Mathematics
    Funding Program
  • Advancing open-source AI for math
    Initiative
  • AI achieves silver-medal standard solving International Mathematical Olympiad problems
    Initiative
  • FrontierMath A math benchmark testing the limits of AI
    Initiative
  • Automating Math by Adam Marblestone
    Whitepapers and Essays
  • Data for Mathematical Copilots: Better Ways of Presenting Proofs for Machine Learning
    Whitepapers and Essays