PICasso：AI 驱动的硅光子器件自主优化设计框架
原标题：PICasso: An AI-Enabled Design Framework for Autonomous Optimization of Silicon Photonic Devices
AI 摘要
arXiv 论文提出 PICasso，一个基于 AI 的硅光子集成电路（PIC）设计框架，能从自然语言规格自动生成、验证和优化电路。PICasso 结合结构化 YAML 生成、PDK 知识注入、自动布局布线、DRC/LVS 验证和 SAX 仿真，并引入包含 36 个任务的基准 PIC-Set。实验显示，PICasso 将高复杂度电路的结构满足率提升至 92.7%，功能满足率至 52%，并将平均插入损耗从 4.98 dB 降至 3.25 dB，展示了 LLM 在光子设计自动化中的实用潜力。
正文节选
PICasso: An AI-Enabled Design Framework for Autonomous Optimization of Silicon Photonic Devices Abstract We present PICasso, an AI-assisted framework for automated synthesis, verification, and optimization of photonic integrated circuits (PICs) from natural-language specifications. PICasso couples a structured NLYAMLGDS generation pipeline with PDK aware knowledge injection, automated placement and routing, DRC/LVS validation, and SAX-based photonic simulation. To systematically evaluate AI-driv