AIDE² paper: self-improving research agent beats the version humans tuned for two years
egrefen · x · 2026-09-24
The arXiv paper on AIDE² is out. It's an RSI (recursive self-improvement) system where AI research agents improve their own research efficiency.
Key result: AIDE² produced a research agent that beats the version the team hand-tuned for two years, and the gains hold on benchmarks the outer loop never saw.
New in the paper: results on transfer across models and comparisons with more AI research agents.
Related event: AIDE²: Self-Improving Research Agent Beats Two Years of Human Tuning(3 posts)→
More from AGI Musings
- Investor: AI diffusion will be slowest in consumer software — Oura, Strava, Labcorp still have no real AI strategy — MartinGTobias · 2026-11-12
- On AI Progress: When Models Lag on Your Load-Bearing Skill, You Can't See Them Improving — dfrsrchtwts · 2026-11-12
- Slack's David Hoang: agents beat people on coordination, proposes 'boundary agents' — davidhoang · 2026-11-12
- CS student mourns coding flow states he'll never experience in the AI era — chrissyykat · 2026-11-12
- Ford's 370% Turnover Led to $5 Days — But ASI Never Quits — krishnan · 2026-11-12
- Against 'verifiable vs. fuzzy': the real axis is how expensive tasks are to grade — dfrsrchtwts · 2026-11-12