Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Investigate AIPS: An Olympiad-level AI System for Algebraic Inequalities #2

Open
deanwampler opened this issue Dec 12, 2024 · 0 comments
Labels
research Research possibly new approaches or problem solutions. tools Possibly useful tools for testing

Comments

@deanwampler
Copy link
Contributor

From the AIPS website:

AIPS (Algebraic Inequality Proving System) is a pioneering Olympiad-level AI system for algebraic inequalities.

By combining symbolic deduction, an efficient search algorithm, and learning methods, AIPS is not only capable of generating large-scale, high-quality inequality theorem dataset, but also effectively solving complex inequality problems. On a test set of 20 International Mathematical Olympiad (IMO) level inequality problems, AIPS successfully solved 10, outperforming state-of-the-art methods. Furthermore, AIPS automatically generated a vast array of non-trivial theorems without human intervention, some of which have been evaluated by professional contestants and deemed to reach the IMO-level. Notably, one theorem was selected as a competition problem in a major city 2024 Mathematical Olympiad.

In our context, what's interesting here is the rigor of this project. Can we learn lessons of use for our project?

@deanwampler deanwampler added tools Possibly useful tools for testing research Research possibly new approaches or problem solutions. labels Dec 12, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
research Research possibly new approaches or problem solutions. tools Possibly useful tools for testing
Development

No branches or pull requests

1 participant