用多智能体系统让电路设计模型自我进化，提升生成质量。
AnalogAgent: Self-Improving Analog Circuit Design Automation with LLM Agents
- 构建代码生成、优化和知识管理三智能体协同工作
- 在基准测试中达97.4%一次通过率，小模型提升48.8%性能
- 无需额外数据或专家干预，适合工业级电路自动化
大语言模型在模拟电路设计自动化中展现出巨大潜力。然而，现有方法多依赖单一模型循环生成、诊断与修正，难以保留关键技术细节且易丢失上下文。为此，我们提出AnalogAgent，一种无需训练的智能体框架，融合基于LLM的多智能体系统（MAS）与自演化记忆（SEM）。该框架由代码生成器、设计优化器与知识策展者协作，将执行反馈转化为可适应的策略手册并检索针对性指导，实现跨任务迁移而无需额外专家反馈、数据库或库。在多个基准测试中，AnalogAgent在Gemini下达到92% Pass@1，GPT-5下达97.4%；使用小型模型（如Qwen-8B）时，平均Pass@1提升48.8%，整体达72.1%，显著增强开源模型在高质量模拟电路设计中的能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。