EEschematic: Multimodal-LLM Based AI Agent for Schematic Generation of Analog Circuit

2025-10-19

AI Summary

Existing LLM-based circuit design methods rely solely on textual representations such as SPICE netlists, lacking visual interpretability and hindering intuitive understanding and verification of topology and device sizing. To address this, we propose a multimodal large language model (MLLM)-driven AI agent framework that integrates textual, visual, and symbolic modalities to enable end-to-end automatic conversion from SPICE netlists to editable schematic diagrams. Our approach introduces six categories of analog subcircuit few-shot layout exemplars and employs a Visual Chain-of-Thought (VCoT) strategy to iteratively refine routing rationality and layout symmetry. Evaluation on benchmark circuits—including CMOS inverters, five-transistor OTAs, and folded cascode amplifiers—demonstrates that the generated schematics achieve high visual fidelity and structural correctness. This significantly enhances design comprehension efficiency and improves the reliability of manual verification.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Circuit schematics play a crucial role in analog integrated circuit design, serving as the primary medium for human understanding and verification of circuit functionality. While recent large language model (LLM)-based approaches have shown promise in circuit topology generation and device sizing, most rely solely on textual representations such as SPICE netlists, which lack visual interpretability for circuit designers. To address this limitation, we propose EEschematic, an AI agent for automatic analog schematic generation based on a Multimodal Large Language Model (MLLM). EEschematic integrates textual, visual, and symbolic modalities to translate SPICE netlists into schematic diagrams represented in a human-editable format. The framework uses six analog substructure examples for few-shot placement and a Visual Chain-of-Thought (VCoT) strategy to iteratively refine placement and wiring, enhancing schematic clarity and symmetry. Experimental results on representative analog circuits, including a CMOS inverter, a five-transistor operational transconductance amplifier (5T-OTA), and a telescopic cascode amplifier, demonstrate that EEschematic produces schematics with high visual quality and structural correctness.

Problem

• Generates analog circuit schematics from SPICE netlists
• Improves visual interpretability for circuit designers
• Enhances schematic clarity and symmetry automatically

Innovation

• Uses multimodal LLM for schematic generation
• Translates SPICE netlists into editable diagrams
• Employs Visual Chain-of-Thought for iterative refinement