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 2607.18772cs.CL

RF-Agent:用于构建射频集成电路设计语言代理的实用框架

RF-Agent: A Practical Framework for Building Language Agents for RFIC Design

  • Rice University(莱斯大学)
  • The George Washington University(乔治·华盛顿大学)

机构由 AI 辅助整理,请以论文原文为准。

Yueqi Xing, Houbo He, Jolie Wang, Erin Ni, Shikai Wang, Qiufeng Li, Weidong Cao, Taiyun Chi

AI总结:

针对大语言模型在射频电路设计应用受限问题,提出RF-Agent框架,通过教科书驱动知识蒸馏创建数据集及基准,研究监督微调与检索增强生成策略,发现特定领域SFT对中小模型提升大,语义检索的RAG表现最佳,为相关工作提供基础。

AI中文摘要:

大语言模型推动了电子设计自动化的快速发展,但其在射频电路设计中的应用因特定领域数据集和标准化基准的稀缺而受限。我们提出了RF-Agent,它通过教科书驱动的知识蒸馏来解决这一差距。一个多智能体问题-思考-解决方案-答案(QTSA)管道将七本经典射频教科书的子章节级语料库转换为首个射频领域推理数据集(超过11000个样本),并带有专用的多项选择基准。在此基准上,我们研究了两种适应策略:监督微调(SFT)和三种检索增强生成(RAG)配置(语义、关键词、混合)。在多个大语言模型家族中,特定领域的SFT显著提高了射频推理能力,特别是对于中小型模型;在RAG配置中,语义检索表现最佳,表明基于嵌入的上下文对齐比简单融合更适合射频推理。该数据集和基准为未来大语言模型辅助射频电路设计的工作提供了可重复使用的基础。

英文摘要:

Large language models (LLMs) have driven rapid progress in electronic design automation (EDA), yet their application to radio-frequency (RF) circuit design remains limited by the scarcity of domain-specific datasets and standardized benchmarks. We present RF-Agent, which addresses this gap through textbook-driven knowledge distillation. A multi-agent Question-Thinking-Solution-Answer (QTSA) pipeline converts a subsection-level corpus from seven canonical RF textbooks into the first-of-its-kind RF-domain reasoning dataset (over 11,000 samples) with a dedicated multiple-choice benchmark. On this benchmark we study two adaptation strategies: supervised fine-tuning (SFT) and three retrieval-augmented generation (RAG) configurations (semantic, keyword, hybrid). Across multiple LLM families, domain-specific SFT significantly improves RF reasoning, especially for small and medium-sized models; among RAG configurations, semantic retrieval performs best, indicating embedding-based context alignment suits RF reasoning better than naive fusion. The dataset and benchmark provide a reusable foundation for future work on LLM-aided RF circuit design.

补充信息

↑