.png){kind=icon}
返回
ModelGen: Automating Semiconductor Parameter Extraction with Large Language Model Agents
.png){kind=icon}
PRE
AI
DOI：10.1145/3736165.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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. Experi-mental 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 168x faster) rather than days or weeks, making parameter extraction more accessible to non-experts while maintaining professional engineer-level accuracy.
Keyword:
Parameter extraction
device model
electronic design automation
large language models
AI agent
bayesian optimization
期刊
A
IF:
2
论文数:
112
被引数:
1.2K
机构
引用论文
.png){kind=icon}
分享收藏
How far are we to GPT-4V? Closing the gap to commercial multimodal models with open-source suites我们离GPT-4V还有多远？利用开源套件缩小与商业多模式模型的差距
PREAI
分享收藏Can LLMs Learn from Previous Mistakes? Investigating LLMs’ Errors to Boost for ReasoningLLMs能从之前的错误中学习吗？探究LLMs的错误以提升推理能力
PREAI
分享收藏
查看更多内容