AetherAI Unveils RSIAgent: Training-Free Recursive Self-Improvement for Agents

AetherAI released RSIAgent, a training-free multi-agent framework that scales experience rather than model parameters, enabling recursive self-improvement and letting open-source model agents reportedly outperform closed-source ones.

2026-09-15 ~ 2026-09-15 · 2 related posts

• RSIAgent: parameter-free self-improvement pushes open-source models past GPT-6 Astra on agent benchmarks — 机器之心 · 2026-09-15
• RSIAgent: training-free multi-agent framework for recursive self-improvement in new environments — AetherLabs-AI · 2026-09-15