AI Autoresearch Loop Beats Two-Year Hand-Tuned Harness in Eight Days
Researchers built AIDE2, an autoresearch‑on‑autoresearch system that ran 100 outer‑loop iterations in eight unattended days. Its best agents, AIDE47 and AIDE85, beat the manually tuned AIDEhuman benchmark that took two years to develop, while also cutting reward‑hacking rates by half.