Self-Evolving Scientific Agent Discovers Generalizable Physically-Reasoned Fluid Control
Researchers have developed a self-evolving scientific agent capable of discovering and refining control policies for physical systems. This agent utilizes large language models and iterative code generation to automate controller construction while maintaining interpretability and physical reasoning. It was demonstrated on a fluid-structure interaction problem, where it autonomously developed a generalized control policy for a dogfish swimmer that could reach various targets without retraining. AI
IMPACT Demonstrates AI's potential for autonomous scientific discovery and control policy generation in complex physical systems.