EvoPINN: Agentic Discovery of Executable Algorithms for Physics-Informed Neural Networks

Abstract

arXiv:2607.26490v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) have emerged as a powerful paradigm for solving partial differential equations (PDEs), yet their performance heavily relies on the manual, trial-and-error engineering of neural representations, loss formulations, and optimization dynamics. While Large Language Models (LLMs) offer a promising avenue for automated design, unconstrained code generation often yields mathematically invalid or numerically unstable