Research

Paper

AI LLM March 25, 2026

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

Authors

Zhixuan Bao, Zhuoyi Lin, Jiageng Wang, Jinhai Hu, Yuan Gao, Yaoxin Wu, Xiaoli Li, Xun Xu

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.

Metadata

arXiv ID: 2603.23910
Provider: ARXIV
Primary Category: cs.AI
Published: 2026-03-25
Fetched: 2026-03-26 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.23910v1</id>\n    <title>AnalogAgent: Self-Improving Analog Circuit Design Automation with LLM Agents</title>\n    <updated>2026-03-25T03:59:02Z</updated>\n    <link href='https://arxiv.org/abs/2603.23910v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.23910v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-25T03:59:02Z</published>\n    <arxiv:comment>16 pages, 6 figures</arxiv:comment>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>Zhixuan Bao</name>\n    </author>\n    <author>\n      <name>Zhuoyi Lin</name>\n    </author>\n    <author>\n      <name>Jiageng Wang</name>\n    </author>\n    <author>\n      <name>Jinhai Hu</name>\n    </author>\n    <author>\n      <name>Yuan Gao</name>\n    </author>\n    <author>\n      <name>Yaoxin Wu</name>\n    </author>\n    <author>\n      <name>Xiaoli Li</name>\n    </author>\n    <author>\n      <name>Xun Xu</name>\n    </author>\n  </entry>"
}