AnalogAgent: Self-Improving Analog Circuit Design Automation with LLM Agents

2026-03-24

AI Summary

This work proposes the first training-free multi-agent framework for large language model (LLM)-driven analog circuit design automation, addressing the limitations of existing single-model iterative approaches that often lose critical details and lack domain depth. The framework integrates a code generator, a design optimizer, and a knowledge curator, augmented with a self-evolving memory mechanism to enable cross-task knowledge transfer and continuous refinement—without requiring expert feedback or external databases. By combining execution-based feedback distillation with retrieval-guided reasoning, the method achieves substantial performance gains on standard benchmarks: Gemini and GPT-5 attain Pass@1 success rates of 92% and 97.4%, respectively, while compact models such as Qwen-8B show an average improvement of 48.8%, reaching an overall Pass@1 rate of 72.1%.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Search and Optimization: Learning to Search
• Cognitive Modeling & Cognitive Systems: Analogy

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Recent advances in large language models (LLMs) suggest strong potential for automating analog circuit design. Yet most LLM-based approaches rely on a single-model loop of generation, diagnosis, and correction, which favors succinct summaries over domain-specific insight and suffers from context attrition that erases critical technical details. To address these limitations, we propose AnalogAgent, a training-free agentic framework that integrates an LLM-based multi-agent system (MAS) with self-evolving memory (SEM) for analog circuit design automation. AnalogAgent coordinates a Code Generator, Design Optimizer, and Knowledge Curator to distill execution feedback into an adaptive playbook in SEM and retrieve targeted guidance for subsequent generation, enabling cross-task transfer without additional expert feedback, databases, or libraries. Across established benchmarks, AnalogAgent achieves 92% Pass@1 with Gemini and 97.4% Pass@1 with GPT-5. Moreover, with compact models (e.g., Qwen-8B), it yields a +48.8% average Pass@1 gain across tasks and reaches 72.1% Pass@1 overall, indicating that AnalogAgent substantially strengthens open-weight models for high-quality analog circuit design automation.

Problem

• analog circuit design
• large language models
• design automation
• context attrition
• domain-specific insight

Innovation

• Multi-Agent System
• Self-Evolving Memory
• Analog Circuit Design Automation
• LLM Agents
• Cross-Task Transfer