用语言模型优化机械连杆设计，提升精度与结构合理性。
Language Models Refine Mechanical Linkage Designs Through Symbolic Reflection and Modular Optimisation
- 结合符号表示与模块化优化，分步改进连杆拓扑与参数。
- 几何误差降低68%，结构有效性提升134%，78.6%迭代有改善。
- 无需微调即掌握可解释的机械推理，适合工程设计场景。
机械连杆设计涉及组合拓扑选择与连续参数拟合。我们展示语言模型可通过符号表示系统性改进连杆设计：语言模型代理探索离散拓扑，数值优化器拟合连续参数。一种符号提升算子将仿真轨迹转换为定性描述、运动标签、时间谓词和结构诊断，供模型在多轮设计中解读。在六个工程相关运动目标和三个开源模型（Llama 3.3 70B、Qwen3 4B、Qwen3 MoE 30B-A3B）上，模块化架构使几何误差最多降低68%，结构有效性最多提升134%，相比单体基线。关键的是，78.6%的迭代优化路径显示可测量改进，系统能正确诊断过约束（56.3%）和欠约束（35.6%）失败模式，并提出基于事实的修正。所有三类模型均无需微调即习得可解释的机械推理策略，表明原理性的符号抽象可弥合生成式AI与工程设计所需数值精度之间的鸿沟。
原文摘要 · Abstract (English)
Designing mechanical linkages involves combinatorial topology selection and continuous parameter fitting. We show that language models can systematically improve linkage designs through symbolic representations. Language model agents explore discrete topologies while numerical optimisers fit continuous parameters. A symbolic lifting operator translates simulator trajectories into qualitative descriptors, motion labels, temporal predicates, and structural diagnostics that models interpret across iterative design cycles. Across six engineering-relevant motion targets and three open-source models (Llama 3.3 70B, Qwen3 4B, Qwen3 MoE 30B-A3B), the modular architecture reduces geometric error by up to 68% and improves structural validity by up to 134% over monolithic baselines. Critically, 78.6% of iterative refinement trajectories show measurable improvement, with the system correctly diagnosing overconstraint (56.3%) and underconstraint (35.6%) failure modes and proposing grounded corrections. Models across all three families acquire interpretable mechanical reasoning strategies without fine-tuning, demonstrating that principled symbolic abstraction bridges generative AI and the numerical precision required for engineering design.
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。