Cover image

When an Optimizer Outgrows Its Teachers

TL;DR for operators Historical optimization runs may be more valuable than their final solutions. They contain records of which candidates were explored, how search populations changed, and which transitions improved the objective. Jian Yao and colleagues investigate whether that experience can train a reusable optimizer. Their Algorithm2Model (A2M) system first imitates existing algorithms, then learns to improve its own search behavior. On continuous BBOB benchmarks, it beats one of its evolutionary teachers on 106 of 120 configurations.1 ...

November 20, 2026 · 8 min · Zelina