← All projects
RSI-Jev
Shanghua-Gao/RSI-Jev MIT HTML Other
rank#140
Typed-decision models (noul / choice / score) trained by a self-improving loop of AI agents — checkpoints, the code that produced them, and every version that failed.
- Stars
- 137
- Forks
- 12
- Open issues
- 0
- Last push
- 2d ago
33 days · 15 → 137
ai-agentsautonomous-researchdecision-modeljevllmrecursive-self-improvementsystem-onetyped-decisions