AIDE² paper: AI research agent self-improves for 8 days, beats 2-year hand-tuned harness

ptkbhv · x · 2026-09-24

Researchers released the arXiv paper on AIDE², a recursive self-improvement (RSI) system where AI research agents improve their own research efficiency.

A notable attempt at turning RSI from theory into measured practice, though generality and reproducibility remain open questions.

Related event: AIDE² Paper: AI Research Agent Self-Tunes in 8 Days, Beating 2 Years of Human Effort(2 posts)→

Original post →

More from coding & agent

coding & agent channel →