GENIE-ASI: Generative Instruction and Executable Code for Analog Subcircuit Identification

2025-08-26

AI Summary

To address the reliance on manual expertise or large-scale labeled datasets for analog subcircuit identification, this paper proposes the first training-free large language model (LLM)-based approach: leveraging in-context learning to generate natural-language instructions, which are automatically translated into executable code for end-to-end subcircuit recognition in SPICE netlists. Key contributions include: (1) the first application of LLMs to automated analog subcircuit identification; (2) enhanced generalization via a code-generation paradigm, eliminating dependence on hand-crafted rules or annotated data; and (3) the construction of the first benchmark dataset dedicated to operational amplifier identification. Experimental results demonstrate F1 scores of 1.0, 0.81, and 0.31 on simple, medium-complexity, and complex circuit structures, respectively—validating the feasibility and promise of LLMs in analog design automation.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Analogy
• Natural Language Processing: (Large) Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• 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

Analog subcircuit identification is a core task in analog design, essential for simulation, sizing, and layout. Traditional methods often require extensive human expertise, rule-based encoding, or large labeled datasets. To address these challenges, we propose GENIE-ASI, the first training-free, large language model (LLM)-based methodology for analog subcircuit identification. GENIE-ASI operates in two phases: it first uses in-context learning to derive natural language instructions from a few demonstration examples, then translates these into executable Python code to identify subcircuits in unseen SPICE netlists. In addition, to evaluate LLM-based approaches systematically, we introduce a new benchmark composed of operational amplifier netlists (op-amps) that cover a wide range of subcircuit variants. Experimental results on the proposed benchmark show that GENIE-ASI matches rule-based performance on simple structures (F1-score = 1.0), remains competitive on moderate abstractions (F1-score = 0.81), and shows potential even on complex subcircuits (F1-score = 0.31). These findings demonstrate that LLMs can serve as adaptable, general-purpose tools in analog design automation, opening new research directions for foundation model applications in analog design automation.

Problem

• Automating analog subcircuit identification without training data
• Reducing reliance on human expertise in circuit analysis
• Generating executable code from natural language instructions

Innovation

• Training-free LLM methodology for identification
• In-context learning generates executable Python code
• New benchmark for systematic LLM evaluation