Abstract
Metasurface inverse design can realize complex optical functionality, but turning a target optical response into executable optimization code still requires substantial expertise in computational electromagnetics and solver-specific software engineering. We present a self-evolving agentic framework that lowers this barrier by coupling a coding agent, explicit human-readable skill files, and a deterministic physics-based evaluator. Instead of updating model weights, it revises the skill files based on solver-grounded feedback while the base model and differentiable solver, which provides the physics simulation and gradients, remain fixed.
On a multi-type benchmark, skill evolution raises same-type task success from 38% to 74%, the fraction of physical criteria met from 0.51 to 0.87, and reduces average attempts from 4.10 to 2.30. On two new-type families, success holds near ceiling on one (0.92 to 0.90) and rises from 0.20 to 0.90 on the other. Skill evolution offers a practical path toward autonomous and accessible inverse-design workflows.
Blogger's Review: This research significantly lowers the entry barrier for metasurface inverse design by combining self-evolving skill files with physical evaluators. It showcases how intelligent agents can facilitate more efficient design processes, providing new insights for automation and accessibility in optical design, which is noteworthy.