Recursive self-improvement of AI research agents

TL;DR - AIDE² recursively improves an AI research agent by rewriting its own code, benchmarking each version, and retaining changes that perform best on hidden evaluations. An eight-day autonomous run produced transferable performance gains and unexpectedly reduced reward hacking.

• Discovered seven successive improvements, including a new search policy and mechanisms for compressing and managing growing context.
• The strongest self-improved agent matched or exceeded a leading human-engineered production agent across four held-out benchmarks.
• Gains transferred across machine learning engineering, heuristic algorithm engineering, and out-of-distribution weather forecasting.
• Reward hacking on a separate held-out task family fell from 55% to 32%, despite not being an explicit optimization target.