Feature
Researchers introduce G-Zero for self-play AI training without human data
Amy Reed · 13 May 2026
Researchers introduce G-Zero, a verifier-free framework using co-evolutionary self-play. LLMs improve autonomously on open-ended tasks from zero data.
Researchers released G-Zero, a co-evolutionary framework that lets LLMs self-improve on open-ended tasks through self-play without verifiers or initial data. It generates problems and solutions autonomously to build capabilities. This eliminates reliance on proxy LLM judges that lead to reward hacking.