让大模型自动完成工业设计闭环优化，解决几何修改难题。
COSMO-Agent: Tool-Augmented Agent for Closed-loop Optimization,Simulation,and Modeling Orchestration
- 用强化学习让大模型协调工具链，自动改设计
- 在25类工业组件上实现90%以上可行方案生成
- 适合需要自动化设计迭代的工程研发团队
工业设计-仿真迭代受制于CAD与CAE之间的语义鸿沟：难以将仿真反馈转化为满足多种耦合约束的有效几何修改。为此，我们提出COSMO-Agent（闭环优化、仿真与建模编排），一个增强型强化学习框架，教会大语言模型完成完整的闭环CAD-CAE流程。具体而言，我们将CAD生成、CAE求解、结果解析与几何修正视为交互式强化学习环境，使大模型学会调用外部工具并修改参数化几何，直至满足约束。为确保学习稳定且可工业应用，我们设计了多约束奖励函数，同时鼓励可行性、工具链鲁棒性和输出结构有效性。此外，我们构建了一个面向工业场景的数据集，涵盖25个组件类别，包含可执行的CAD-CAE任务，支持真实训练与评估。实验表明，经训练后的小型开源大模型在约束驱动设计任务中表现显著提升，超越大型开源及强闭源模型，在可行性、效率和稳定性方面均更优。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。