Tool-Augmented Agent for Closed-loop Optimization,Simulation,and Modeling Orchestration

The COSMO-Agent framework uses tool-augmented reinforcement learning to teach LLMs to bridge the CAD-CAE semantic gap, enabling closed-loop optimization in industrial design. It leverages an interactive RL environment for CAD generation, CAE solving, result parsing, and geometry revision, guided by a multi-constraint reward for feasibility and robustness.