Code-to-Harness: Distilling Black-Box Optimizers from Self-Play

The paper investigates whether an agent can learn a numerical search strategy through executable practice and then encode that strategy as text. By repeatedly writing and evaluating optimizer programs, the agent distills a 197‑word text called Harness A, which significantly reduces regret for Gemini Flash and other language‑model executors, matching the performance of classical Gaussian‑process Bayesian optimization. An independent replication produced a different but equally effective text, Harness B, and the framework also achieved the lowest regret on a sealed YouTube reward‑tuning benchmark.

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.

• llms
• agents
• reinforcement-learning
• benchmarks