Recursive self-improvement of AI research agents

The paper introduces AIDE^2, an AI research agent that recursively improves its own code by proposing, benchmarking, and selecting modifications. Over an eight‑day autonomous run, it achieved seven successive improvements—including new search policies and memory mechanisms—that transferred to four held‑out benchmarks in machine learning, algorithm engineering, and weather forecasting. The agent’s best version matched or outperformed a top human‑engineered production research agent and also reduced reward‑hacking rates, despite never optimizing for that metric.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

• agents
• benchmarks