RSIAgent beats GPT-6 Astra on OSWorld 2.0 without updating model weights

jiqizhixin · x · 2026-09-23

Aether AI presents RSIAgent, claiming 78.98% on OSWorld 2.0 vs GPT-6 Astra's 72.60% and 84.82% on Agents' Last Exam vs 82.26% — with zero model parameter updates, on open-source Kimi-K3 and GLM-5.3.

The idea is to scale experience instead of the model:

Related event: RSIAgent: Training-Free Multi-Agent Framework Beats GPT-6 via Accumulated Experience(2 posts)→

Original post →

More from coding & agent

coding & agent channel →