从提示到原型：面向前沿大语言模型驱动的射频工程工作流
From Prompt to Prototype: Towards a Frontier LLM Driven RF Engineering Workflow
浏览论文内容
中文总结 AI 辅助
该研究开发了前沿LLM驱动的射频工程工作流，让LLM智能体自主操作多款专业EDA工具完成射频硬件设计，仅需工程师提供关键输入，拓展了LLM在专业工程领域的应用。
中文摘要 AI 辅助
智能编码环境赋予前沿大语言模型（LLM）直接访问工作站终端、文件系统和软件的权限，本研究证明其可延伸至专业射频（RF）硬件设计：一款集成在同一块印刷电路板（PCB）上的有源GNSS L1波段天线——包含圆极化贴片、表面声波（SAW）预滤波器及两级低噪声放大器（LNA）——被设计、优化并达到可制造标准。该LLM智能体通过脚本接口自主操作CST Studio Suite、Keysight ADS和KiCad，工程师仅需提供规格参数、权衡决策及设计评审。本文还讨论了该工作流、相关结果及射频工程师角色的演变。
英文摘要
Agentic coding environments give a frontier large language model (LLM) direct access to a workstation's terminal, file system, and software. This work demonstrates they extend to professional RF hardware design: an active GNSS L1-band antenna - a circularly polarized patch, surface acoustic wave (SAW) prefilter, and two-stage low-noise amplifier (LNA) on one printed circuit board (PCB) - was designed, optimized, and made manufacturing-ready. The LLM agent autonomously operated CST Studio Suite, Keysight ADS, and KiCad via scripting interfaces. Engineer input was limited to the specification, trade-off decisions, and design reviews. Workflow, results, and the RF engineer's evolving role are discussed.
发表机构
- Ruhr-University Bochum（鲁尔大学波鸿）
- TH Köln - University of Applied Sciences（科隆应用科学大学）
机构由 AI 辅助整理，请以论文原文为准。
