Shanghua-Gao/RSI-Jev

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.

语言：HTML · GitHub 星标：127 · Fork：11

话题：ai-agents · autonomous-research · decision-model · jev · llm · recursive-self-improvement · system-one · typed-decisions

在 GitHub 上查看原仓库