arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.17002cs.LG
收藏

EEschematic:基于多模态大语言模型的模拟电路原理图生成 AI 智能体

EEschematic: Multimodal-LLM Based AI Agent for Schematic Generation of Analog Circuit

School of Engineering The University of Edinburgh Edinburgh, UK(工程学院 苏格兰爱丁堡大学)

Chang Liu, Danial Chitnis

AI总结:

本文提出基于 MLLM 的 AI 智能体 EEschematic,融合多模态信息、少样例布局与 VCoT 迭代优化,将 SPICE 网表自动转换为可编辑且结构正确的模拟电路原理图。

摘要:

电路原理图在模拟集成电路设计中发挥着关键作用,是人类理解和验证电路功能的主要媒介。尽管近期基于大语言模型(LLM)的方法已在电路拓扑生成和器件尺寸确定方面展现出潜力,但大多数方法仅依赖 SPICE 网表等文本表示,对电路设计者而言缺乏视觉可解释性。为解决这一局限,我们提出 EEschematic,这是一种基于多模态大语言模型(MLLM)的自动模拟原理图生成 AI 智能体。EEschematic 融合文本、视觉和符号模态,将 SPICE 网表转换为以人类可编辑格式表示的原理图。该框架使用六个模拟子结构示例进行少样例布局,并采用视觉思维链(VCoT)策略迭代优化布局和布线,从而提升原理图的清晰度与对称性。在包括 CMOS 反相器、五管运算跨导放大器(5T-OTA)和套筒式共源共栅放大器在内的代表性模拟电路上的实验结果表明,EEschematic 生成的原理图具有较高的视觉质量和结构正确性。

英文摘要:

Circuit schematics play a crucial role in analog integrated circuit design, serving as the primary medium for human understanding and verification of circuit functionality. While recent large language model (LLM)-based approaches have shown promise in circuit topology generation and device sizing, most rely solely on textual representations such as SPICE netlists, which lack visual interpretability for circuit designers. To address this limitation, we propose EEschematic, an AI agent for automatic analog schematic generation based on a Multimodal Large Language Model (MLLM). EEschematic integrates textual, visual, and symbolic modalities to translate SPICE netlists into schematic diagrams represented in a human-editable format. The framework uses six analog substructure examples for few-shot placement and a Visual Chain-of-Thought (VCoT) strategy to iteratively refine placement and wiring, enhancing schematic clarity and symmetry. Experimental results on representative analog circuits, including a CMOS inverter, a five-transistor operational transconductance amplifier (5T-OTA), and a telescopic cascode amplifier, demonstrate that EEschematic produces schematics with high visual quality and structural correctness.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑