Agent speeds up calibration of oxide semiconductor transistor models
Agentic TCAD Calibration Workflow for Oxide Semiconductor Transistors
Artificial IntelligenceMachine Learning
Summary
Calibrating computer models to match how new oxide semiconductor transistors behave is usually slow and needs experts. The authors created a system where a smart agent helps adjust the model parameters automatically by testing different changes and only keeping those that improve the match. This method was tested on a specific transistor type and showed better accuracy across different conditions without manual tuning. It offers a faster way to develop reliable models for new transistor technologies.
What this means in practice
- •For semiconductor device engineers: Use the agentic workflow to automate and accelerate model calibration for oxide semiconductor device simulations, reducing dependency on expert manual fitting.
- •For integrated circuit designers: Obtain more reliable transistor models that maintain accuracy across different biases and geometries for improved circuit design predictions.
Authors
Gyujun Jeong, Junmo Lee, Sungwon Cho, Woohyun Hwang, Kwangyou Seo, Suhwan Lim, Wanki Kim, Daewon Ha, Rishi Ranade, Kihang Youn, Ram Cherukuri, Yiyi Wang, Asif Khan, Shimeng Yu
Abstract
Experimental TCAD calibration is essential for predictive technology modeling of emerging oxide semiconductor transistors. However, it remains time-consuming and expert dependent because of model ambiguity. Multiple physical models and parameter sets can reproduce the same measured transfer characteristics, while local fitting alone cannot uniquely identify the underlying device physics. We present the first demonstration of an agentic TCAD calibration workflow for a fabricated bottom-gate In--W--O (BG-IWO) transistor. Starting from the measured transfer curve and device information, the workflow uses measurement--TCAD residuals and local sensitivity tests to select bounded parameter corrections or evaluate additional physical models, and accept only updates that improve device metrics. The LLM agent orchestrates the workflow, while Sentaurus governs the device physics. For the 2\%-W reference device, five agent-suggested updates yield a fixed calibrated model, reducing the multi-metric device objective $J$ by 14.3$\times$. Maximum $V_{\mathrm{th}}$/$I_{\mathrm{on}}$ errors are 36.1~mV/0.022 decade for varying-drain-bias tests and 46.2~mV/0.062 decade for varying-channel-length tests, demonstrating model transferability across bias and geometry rather than a local parameter fit. W-composition tests provide process-sensitive insight. This agentic workflow provides a faster route to model development for emerging device technologies.