RSIHub
simple-agent-lab tarafından
A research framework for principled agent self-improvement under frozen evaluators and declared mutation boundaries, recording verifiable lineage to make it reproducible and auditable.
README'den
A file-based evolution framework for evaluator-driven learning, reproducible candidate lineage, and controllable modification. RSIHub Website · What RSIHub Does · How It Works · What Can Evolve · Recipes · Showcase · Quick Start · Documentation News 2026-10: Our paper, RSIHub: A Composable Framework for Agent-Evolution Methods, has been accepted to the NeurIPS 2026 Meta-Agents Workshop! [!TIP] New to AI-for-AI and agent self-improvement? Start with the curated Awesome-AI4AI paper list, read the AI4AI Survey (PDF) for the full landscape, and follow the AI4AI blog for ongoing notes from Simple…
Projenin GitHub'daki README dosyasından alıntı.
Beceriler
Açık kaynaklı bir proje — kodu inceleyin ve GitHub'dan kendi sunucunuzda barındırın.