With the continued scaling of advanced technology nodes, the design-technology co-optimization (DTCO) paradigm has become increasingly critical, rendering efficient device design and optimization essential. In the domain of TCAD simulation, however, the scarcity of open-source resources hinders language models from generating valid TCAD code. To overcome this limitation, we construct an open-source TCAD dataset curated by experts and fine-tune a domain-specific model for TCAD code generation. Building on this foundation, we propose AgenticTCAD, a natural language - driven multi-agent framework that enables end-to-end automated device design and optimization. Validation on a 2 nm nanosheet FET (NS-FET) design shows that AgenticTCAD achieves the International Roadmap for Devices and Systems (IRDS)-2024 device specifications within 4.2 hours, whereas human experts required 7.1 days with commercial tools.

翻译：随着先进技术节点的持续微缩，设计-技术协同优化（DTCO）范式变得日益关键，这使得高效的器件设计与优化至关重要。然而，在TCAD仿真领域，开源资源的匮乏阻碍了语言模型生成有效的TCAD代码。为克服这一局限，我们构建了一个由专家筛选的开源TCAD数据集，并微调了一个面向TCAD代码生成的领域专用模型。在此基础上，我们提出了AgenticTCAD，这是一个由自然语言驱动的多智能体框架，能够实现端到端的自动化器件设计与优化。在2纳米纳米片场效应晶体管（NS-FET）设计上的验证表明，AgenticTCAD可在4.2小时内达到国际器件与系统路线图（IRDS）-2024的器件规格要求，而人类专家使用商业工具则需要7.1天。