Meta’s SPICE framework lets AI systems teach themselves to reason

Researchers at Meta FAIR and the National University of Singapore have developed a new reinforcement learning framework for self-improving AI systems. Called Self-Play In Corpus Environments (SPICE), the framework pits two AI agents against each other, creating its own challenges and gradually improving without human supervision.While currently a proof-of-concept, this self-play mechanism could provide a basis for future AI systems that can dynamically adapt to their environments, making them mo