LLM-based AI Agent for Sizing of Analog and Mixed Signal Circuit

2025-04-14

AI Summary

Analog/mixed-signal (AMS) circuit transistor sizing remains heavily reliant on expert intuition, while existing EDA tools employing machine learning suffer from excessive iterative simulation, insufficient domain-knowledge integration, and dependence on labeled training data. Method: This paper introduces the first large language model (LLM)-based intelligent agent framework for end-to-end AMS design closure. It tightly couples Claude 3.5 Sonnet with SPICE simulation, Python-based data parsing, and structured prompt engineering to enable autonomous sizing optimization. Contribution/Results: The framework pioneers LLMs as self-directed agents within the AMS design flow—leveraging domain-aware reasoning and tool-calling capabilities to eliminate reliance on labeled datasets and trial-and-error iterations. LLM selection is validated across seven fundamental circuit topologies; applied to an operational amplifier featuring complementary input and class-AB output stages, it achieves up to 60% constraint satisfaction rate under three distinct multi-objective performance specifications.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

The design of Analog and Mixed-Signal (AMS) integrated circuits (ICs) often involves significant manual effort, especially during the transistor sizing process. While Machine Learning techniques in Electronic Design Automation (EDA) have shown promise in reducing complexity and minimizing human intervention, they still face challenges such as numerous iterations and a lack of knowledge about AMS circuit design. Recently, Large Language Models (LLMs) have demonstrated significant potential across various fields, showing a certain level of knowledge in circuit design and indicating their potential to automate the transistor sizing process. In this work, we propose an LLM-based AI agent for AMS circuit design to assist in the sizing process. By integrating LLMs with external circuit simulation tools and data analysis functions and employing prompt engineering strategies, the agent successfully optimized multiple circuits to achieve target performance metrics. We evaluated the performance of different LLMs to assess their applicability and optimization effectiveness across seven basic circuits, and selected the best-performing model Claude 3.5 Sonnet for further exploration on an operational amplifier, with complementary input stage and class AB output stage. This circuit was evaluated against nine performance metrics, and we conducted experiments under three distinct performance requirement groups. A success rate of up to 60% was achieved for reaching the target requirements. Overall, this work demonstrates the potential of LLMs to improve AMS circuit design.

Problem

• Automating transistor sizing in AMS circuit design
• Reducing manual effort in analog IC design
• Improving circuit performance with LLM-based optimization

Innovation

• LLM-based AI agent for AMS circuit sizing
• Integration with simulation tools and data analysis
• Prompt engineering for performance optimization