AaLLM: An End-to-End Analog Circuit Design Framework from Topology Generation to Sizing Using Large Language Models

📄 arXiv: 2608.13472v1 📥 PDF

作者: Mohammed Ayman Habib, Rylan Hart, Morteza Fayazi

分类: eess.SY, cs.AI

发布日期: 2026-08-13


💡 一句话要点

提出AaLLM框架以解决模拟电路设计中的效率问题

🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)

关键词: 模拟电路设计 大型语言模型 自动化设计 知识库创建 多代理系统

📋 核心要点

  1. 现有的LLM方法在模拟电路设计中往往只关注单一方面,导致效率低下且容易出错。
  2. AaLLM框架通过整合拓扑生成与尺寸调整,提供一个全面的电路设计解决方案,自动化知识库的创建。
  3. 实验表明,AaLLM在多个电路拓扑测试中显著减少了SPICE调用次数和墙钟时间,提升了设计效率。

📝 摘要(中文)

模拟电路设计是一个耗时且迭代的过程,依赖于专家的直觉。现有的基于大型语言模型(LLM)的方法往往只关注电路拓扑生成或尺寸调整,缺乏整体性,且容易出现错误。本文提出了AaLLM,一个开源的端到端多代理LLM工作流,能够根据用户规格生成相应的电路网表,涵盖拓扑生成和电路尺寸调整。AaLLM通过自动创建知识库来减少手动数据收集的繁琐,采用RAG模型模拟电路设计专业知识,并引入三代理反馈系统以优化设计过程。实验结果显示,AaLLM生成的新拓扑在性能上与已知拓扑相当,某些电路的性能甚至提高了3倍,同时在推理时SPICE调用次数减少了3到4.5倍,墙钟时间减少了40倍。

🔬 方法详解

问题定义:论文旨在解决现有模拟电路设计方法的低效和片面性,现有方法往往只关注电路的尺寸调整或拓扑生成,导致设计过程繁琐且容易出错。

核心思路:AaLLM通过整合拓扑生成与电路尺寸调整,提供一个端到端的解决方案,利用大型语言模型的自然语言推理能力来优化电路设计过程。

技术框架:AaLLM的整体架构包括三个主要模块:知识库创建、设计代理和反馈系统。知识库从研究论文和教材中自动生成,设计代理负责确定电路组件值,反馈系统则通过评估和审查来优化设计。

关键创新:AaLLM的创新在于其三代理反馈系统,分别为设计者、评论者和评估者,能够有效减少电路尺寸调整的迭代次数,提升设计效率。与现有方法相比,AaLLM能够生成创新的电路拓扑,避免了对传统拓扑的依赖。

关键设计:在设计过程中,AaLLM采用了RAG模型来模拟电路设计的专业知识,确保生成的电路设计既符合用户需求,又具备高效性。

🖼️ 关键图片

fig_0
img_1
img_2

📊 实验亮点

实验结果显示,AaLLM在多个电路拓扑测试中,SPICE调用次数减少了3到4.5倍,墙钟时间减少了40倍,生成的新拓扑在性能上与已知拓扑相当,某些电路的性能提升高达3倍,显著提高了设计效率。

🎯 应用场景

AaLLM框架在模拟电路设计领域具有广泛的应用潜力,能够为电子工程师提供高效的设计工具,减少设计周期,提高设计质量。未来,该框架还可以扩展到其他领域,如集成电路设计和系统级设计,推动自动化设计的发展。

📄 摘要(原文)

Analog circuit design is a time-consuming, iterative process in a nonlinear and high-dimensional design space that relies heavily on expert intuition. Among recent developments, LLMs have introduced a promising approach by bringing natural language reasoning to circuit design tasks. The majority of conventional LLM-based approaches provide fragmented solutions that focus either only on sizing or topology generation. These methods require adding specific technical knowledge manually, which is inefficient and prone to hallucinations during circuit sizing. Moreover, the inherent trade-off in meeting different specs makes current approaches iterative and tedious. Another shortcoming is the inability to create innovative topologies, which may lead to sub-optimal designs due to reliance on conventional topologies. In this paper, we present AaLLM, an open-source end-to-end multi-agent LLM workflow that takes user specs as input and outputs the appropriate netlist, encompassing both topology generation and circuit sizing. AaLLM automates the creation of a relevant knowledge base from research papers and textbooks to combat tedious manual data collection. A RAG model is implemented to emulate circuit design expertise using this knowledge base. Moreover, AaLLM uses a novel tri-agent feedback system comprising a Designer that determines circuit component values, a Critic that scrutinizes these values, and an Evaluator that minimizes circuit sizing iterations by arbitrating between the other two agents. AaLLM-generated novel topologies achieve a figure of merit (FoM) comparable to that of known topologies, and up to 3x higher for certain circuits. Testing on several circuit topologies, our results show a 3x - 4.5x decrease in the number of SPICE calls at inference when compared to SOTA multi-agent LLM pipelines. The results also show a 40x decrease in wall-clock time compared to existing approaches.