用多智能体和分层记忆自动优化模拟电路设计，效率提升数十倍。
AnalogSAGE: Self-evolving Analog Design Multi-Agents with Stratified Memory and Grounded Experience
- 三阶段智能体协作，分层记忆存储经验，逐步优化电路设计。
- 在10个任务中整体通过率提升10倍，首次通过率提高48倍。
- 适合芯片设计自动化研究者，开源可复现，支持真实工艺验证。
模拟电路设计依赖大量专业知识与经验，通常需依赖人工直觉进行拓扑生成与参数调优。现有基于大模型的方法多依赖提示驱动的网表生成或预设拓扑模板，难以满足复杂规格要求。我们提出 AnalogSAGE，一个开源的自进化多智能体框架，通过四层分层记忆协调三阶段智能体探索，实现基于仿真反馈的迭代优化。为保障可复现性与通用性，我们公开源代码。基准测试涵盖十个难度各异的运算放大器设计任务，在开源 SKY130 PDK 与 ngspice 环境下评估，AnalogSAGE 实现整体通过率提升10倍、首次通过率提升48倍，参数搜索空间缩小4倍，表明分层记忆与仿真引导推理显著增强了模拟设计自动化的可靠性与自主性。
原文摘要 · Abstract (English)
Analog circuit design remains a knowledge- and experience-intensive process that relies heavily on human intuition for topology generation and device parameter tuning. Existing LLM-based approaches typically depend on prompt-driven netlist generation or predefined topology templates, limiting their ability to satisfy complex specification requirements. We propose AnalogSAGE, an open-source self-evolving multi-agent framework that coordinates three-stage agent explorations through four stratified memory layers, enabling iterative refinement with simulation-grounded feedback. To support reproducibility and generality, we release the source code. Our benchmark spans ten specification-driven operational amplifier design problems of varying difficulty, enabling quantitative and cross-task comparison under identical conditions. Evaluated under the open-source SKY130 PDK with ngspice, AnalogSAGE achieves a 10$\times$ overall pass rate, a 48$\times$ Pass@1, and a 4$\times$ reduction in parameter search space compared with existing frameworks, demonstrating that stratified memory and grounded reasoning substantially enhance the reliability and autonomy of analog design automation in practice.
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。