AgenticTCAD: A LLM-based Multi-Agent Framework for Automated TCAD Code Generation and Device Optimization

TL;DR

AgenticTCAD is a novel multi-agent framework leveraging a fine-tuned language model and an expert-curated dataset to automate TCAD code generation and device optimization, significantly reducing design time.

Contribution

This work introduces a domain-specific dataset and a multi-agent system for automated TCAD code generation and device optimization, advancing AI-driven semiconductor design.

Findings

Achieves IRDS-2024 specifications in 4.2 hours

Reduces design time from 7.1 days to hours

Demonstrates effective automation in advanced device design

Abstract

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.