Analog mixed-signal circuit sizing involves complex trade-offs within high-dimensional design spaces. Existing automatic analog circuit sizing approaches often underutilize circuit schematics and lack the explainability required for industry adoption. To tackle these challenges, we propose a Vision Language Model-optimized collaborative agent design workflow (VLM-CAD), which analyzes circuits, optimizes DC operating points, performs inference-based sizing and executes external sizing optimization. We integrate Image2Net to annotate circuit schematics and generate a structured JSON description for precise interpretation by Vision Language Models. Furthermore, we propose an Explainable Trust Region Bayesian Optimization method (ExTuRBO) that employs collaborative warm-starting from agent-generated seeds and offers dual-granularity sensitivity analysis for external sizing optimization, supporting a comprehensive final design report. Experiment results on amplifier sizing tasks using 180nm, 90nm, and 45nm Predictive Technology Models demonstrate that VLM-CAD effectively balances power and performance, achieving a 100% success rate in optimizing an amplifier with a complementary input and a class-AB output stage, while maintaining total runtime under 43 minutes across all experiments.

翻译：模拟混合信号电路的尺寸优化涉及高维设计空间内的复杂权衡。现有的自动模拟电路尺寸优化方法往往未能充分利用电路原理图，且缺乏工业应用所需的可解释性。为应对这些挑战，我们提出了一种视觉语言模型优化的协同智能体设计流程（VLM-CAD），该流程能够分析电路、优化直流工作点、执行基于推理的尺寸优化并运行外部尺寸优化。我们集成Image2Net工具对电路原理图进行标注，并生成结构化JSON描述，以确保视觉语言模型能够精确解读。此外，我们提出了一种可解释的信任域贝叶斯优化方法（ExTuRBO），该方法采用智能体生成种子的协同热启动策略，并提供双粒度灵敏度分析以支持外部尺寸优化，最终生成全面的设计报告。基于180nm、90nm和45nm预测技术模型的放大器尺寸优化实验结果表明，VLM-CAD能有效平衡功耗与性能，在优化具有互补输入级和AB类输出级的放大器时实现了100%的成功率，且所有实验的总运行时间均控制在43分钟以内。