AgenticTCAD: A LLM-based Multi-Agent Framework for Automated TCAD Code Generation and Device Optimization
This addresses the problem of inefficient device optimization for semiconductor designers by providing an automated framework, though it is incremental as it builds on existing LLM and multi-agent methods.
The paper tackles the challenge of generating valid TCAD code for device design by constructing an open-source dataset and fine-tuning a domain-specific model, resulting in AgenticTCAD, a multi-agent framework that automatedly designs a 2 nm nanosheet FET meeting IRDS-2024 specifications in 4.2 hours compared to 7.1 days for human experts.
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.