arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.20190cs.AIcs.GR
收藏

具有工具增强的代理用于闭环优化、仿真和建模协调

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

Northwestern Polytechnical University(西北工业大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室)

Liyuan Deng, Shujian Deng, Yongkang Chen, Yongkang Dai, Zhihang Zhong, Linyang Li, Xiao Sun, Yilei Shi, Huaxi Huang

AI总结:

本文提出COSMO-Agent框架,通过强化学习使大语言模型完成闭环CAD-CAE流程,解决CAD-CAE语义鸿沟问题,提升工业设计仿真优化的可行性、效率和稳定性。

摘要:

迭代的工业设计-仿真优化受到CAD-CAE语义鸿沟的限制:在多样的、耦合的约束条件下,将仿真反馈转化为有效的几何编辑。为填补这一鸿沟,我们提出了COSMO-Agent(闭环优化、仿真和建模协调),一种具有工具增强的强化学习(RL)框架,该框架教会大语言模型完成闭环CAD-CAE流程。具体来说,我们将CAD生成、CAE求解、结果解析和几何修改视为一个交互式RL环境,其中LLM学习协调外部工具并修改参数化几何体,直到满足约束条件。为了使这种学习稳定且适用于工业应用,我们设计了多约束奖励,共同鼓励可行性、工具链鲁棒性和结构化输出的有效性。此外,我们贡献了一个与行业对齐的数据集,涵盖了25个组件类别,具有可执行的CAD-CAE任务,以支持现实的训练和评估。实验表明,COSMO-Agent训练显著提高了小开源LLM在约束驱动设计中的表现,超过了大开源和强闭源模型在可行性、效率和稳定性方面。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑