ADO-LLM is a novel framework that leverages large language models to enhance Bayesian Optimization for automated analog circuit design, significantly improving design productivity.

• Integrates LLM in-context learning capabilities with traditional Bayesian Optimization methods
• Overcomes limitations of black box Gaussian Process models used in conventional approaches
• Enhances design productivity by reducing the need for substantial human expertise and involvement
• Demonstrates practical applications across various circuit topologies and technologies

This innovation addresses a critical bottleneck in engineering productivity by automating complex analog design tasks that traditionally required significant human expertise, potentially transforming semiconductor design workflows.

ADO-LLM: Analog Design Bayesian Optimization with In-Context Learning of Large Language Models