Search papers, labs, and topics across Lattice.
COSMO-Agent is introduced as a tool-augmented reinforcement learning framework that trains LLMs to perform closed-loop CAD-CAE optimization by orchestrating external tools and revising parametric geometries. The framework addresses the CAD-CAE semantic gap by casting the design process as an interactive RL environment and using a multi-constraint reward function to encourage feasibility, robustness, and structured output. Experiments on a new industry-aligned dataset demonstrate that COSMO-Agent significantly improves the performance of smaller LLMs, surpassing larger open-source and closed-source models in constraint-driven design tasks.
Small, open-source LLMs can now outperform larger, closed-source models in complex industrial design tasks by learning to orchestrate CAD/CAE tools within a reinforcement learning framework.
Iterative industrial design-simulation optimization is bottlenecked by the CAD-CAE semantic gap: translating simulation feedback into valid geometric edits under diverse, coupled constraints. To fill this gap, we propose COSMO-Agent (Closed-loop Optimization, Simulation, and Modeling Orchestration), a tool-augmented reinforcement learning (RL) framework that teaches LLMs to complete the closed-loop CAD-CAE process. Specifically, we cast CAD generation, CAE solving, result parsing, and geometry revision as an interactive RL environment, where an LLM learns to orchestrate external tools and revise parametric geometries until constraints are satisfied. To make this learning stable and industrially usable, we design a multi-constraint reward that jointly encourages feasibility, toolchain robustness, and structured output validity. In addition, we contribute an industry-aligned dataset that covers 25 component categories with executable CAD-CAE tasks to support realistic training and evaluation. Experiments show that COSMO-Agent training substantially improves small open-source LLMs for constraint-driven design, exceeding large open-source and strong closed-source models in feasibility, efficiency, and stability.
