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

TL;DR

AnalogAgent introduces a multi-agent, memory-augmented framework leveraging large language models to automate analog circuit design, significantly improving success rates and enabling effective transfer across tasks without extra data or expert input.

Contribution

It presents a novel training-free, multi-agent system with self-evolving memory that enhances LLM-based analog circuit design automation and transfer learning capabilities.

Findings

Achieves up to 97.4% Pass@1 on benchmarks.

Improves open-weight model performance by 48.8%.

Substantially enhances analog design automation quality.

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.