EUVIMEDEUVIMED entdecken
Crossref

ModelGen: Automating Semiconductor Parameter Extraction with Large Language Model Agents

Yangbo Wei, Li Huang, Qi Feng, Zhanfei Chen, Jinlong Yan, Ting-Jung Lin, Zhen Huang, Kun Ren, Wei Xing, Lei He

ACM Transactions on Design Automation of Electronic Systems · 30.11.2025 · 30 (6) · 1-26

DOI: 10.1145/3736165 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Design Automation of Electronic Systems, online erschienen am 17.10.2025. Verfasst von Yangbo Wei und 9 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: Ningbo Natural Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Device models require large numbers of parameters to characterize complex physical effects. Although the latest advancements in machine learning and automated tools have drastically improved efficiency over the classic methods, they still demand a considerable amount of human intervention in the loop to gain accuracy. This drastically limits further automation. Inspired by the success of Multimodal Large Language Models (MLLMs) in addressing tasks across diverse fields, we propose ModelGen, the first in-depth study to leverage MLLMs with RAG (Retrieval-Augmented Generation) to significantly reduce human effort in parameter extraction for compact model. Our contributions include (1) Automated Agentic Workflow Construction that learns to build and refine extraction workflows through iterative optimization, (2) MLLM Judge, a visual scoring mechanism that evaluates fitting quality using actual device characteristic plots rather than simple numerical metrics, and (3) Model-specific RAG for providing relevant domain knowledge during the extraction process. Experimental results demonstrate that ModelGen achieves a 26.8%–33.1% improvement in pass@1,3,5 compared to base LLM methods. The system completes complex model extractions for BSIMs and ASM-HEMT in hours (up to 168× faster) rather than days or weeks, making parameter extraction more accessible to non-experts while maintaining professional engineer-level accuracy.

Förderung

  • Ningbo Natural Science Foundation

Zitieren

APA

Wei, Y., Huang, L., Feng, Q., Chen, Z., Yan, J., Lin, T., Huang, Z., Ren, K., Xing, W., & He, L. (2025). ModelGen: Automating Semiconductor Parameter Extraction with Large Language Model Agents. ACM Transactions on Design Automation of Electronic Systems, 30(6), 1-26. https://doi.org/10.1145/3736165

Vancouver

Wei Y, Huang L, Feng Q, Chen Z, Yan J, Lin T, et al. ModelGen: Automating Semiconductor Parameter Extraction with Large Language Model Agents. ACM Transactions on Design Automation of Electronic Systems. 2025;30(6):1-26. doi:10.1145/3736165

BibTeX
@article{Wei2025,
  author = {Wei, Yangbo and Huang, Li and Feng, Qi and Chen, Zhanfei and Yan, Jinlong and Lin, Ting-Jung and Huang, Zhen and Ren, Kun and Xing, Wei and He, Lei},
  title = {ModelGen: Automating Semiconductor Parameter Extraction with Large Language Model Agents},
  journal = {ACM Transactions on Design Automation of Electronic Systems},
  year = {2025},
  volume = {30},
  number = {6},
  pages = {1--26},
  doi = {10.1145/3736165}
}
Kostenlos starten →