AI Gamestore: Scalable, Open-Ended Evaluation of Machine General Intelligence with Human Games

By: Lance Ying, Ryan Truong, Prafull Sharma, Kaiya Ivy Zhao, Nathan Cloos, Kelsey R. Allen, Thomas L. Griffiths, Katherine M. Collins, José Hernández-Orallo, Phillip Isola, Samuel J. Gershman, Joshua B. Tenenbaum

Published: 2026-02-20

View on arXiv →
#cs.AI

Abstract

This paper introduces "AI Gamestore," a platform designed for the scalable and open-ended evaluation of machine general intelligence through human games. This approach provides a robust framework for assessing AI capabilities beyond narrow tasks, offering valuable insights into the development of more generally intelligent AI systems with broad real-world applicability.

FEEDBACK

Projects

No projects yet

AI Gamestore: Scalable, Open-Ended Evaluation of Machine General Intelligence with Human Games | ArXiv Intelligence