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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fan, Guangxi, Ma, Tianliang, Sun, Xuguang, Wang, Xun, Low, Kain Lu, Shao, Leilai
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908761122144256
author Fan, Guangxi
Ma, Tianliang
Sun, Xuguang
Wang, Xun
Low, Kain Lu
Shao, Leilai
author_facet Fan, Guangxi
Ma, Tianliang
Sun, Xuguang
Wang, Xun
Low, Kain Lu
Shao, Leilai
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_23742
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AgenticTCAD: A LLM-based Multi-Agent Framework for Automated TCAD Code Generation and Device Optimization
Fan, Guangxi
Ma, Tianliang
Sun, Xuguang
Wang, Xun
Low, Kain Lu
Shao, Leilai
Software Engineering
Artificial Intelligence
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.
title AgenticTCAD: A LLM-based Multi-Agent Framework for Automated TCAD Code Generation and Device Optimization
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2512.23742