用大模型辅助模拟电路设计，发现其生成不稳定且依赖数据格式。
LLMs for Analog Circuit Design Continuum (ACDC)
- 测试不同数据表示对模型表现的影响，探索人机协同设计路径。
- 小模型易受格式影响，大模型仍出现设计不一致和泛化差问题。
- 适合关注工程领域AI可靠性的研究者和芯片设计工程师。
大型语言模型（LLMs）和Transformer架构在自然语言任务中展现出卓越的推理与生成能力，但在真实工程领域的可靠性与鲁棒性尚未充分验证，限制了其在人机协作工作流中的实际应用。本文研究了LLMs在模拟电路设计中的适用性与一致性——该任务需要领域特定推理、遵守物理约束并采用结构化表示。重点考察了数据表示方式对模型行为的影响，并对比了小型模型（如T5、GPT-2）与大型基础模型（如Mistral-7B、GPT-oss-20B）在不同训练条件下的表现。结果揭示了关键可靠性挑战：对数据格式敏感、生成设计不稳定，以及在未见电路配置上泛化能力有限。这些发现为大模型作为增强人类能力工具的潜力与局限提供了早期证据，有助于设计可部署、可靠的通用模型以应对结构化现实应用。
原文摘要 · Abstract (English)
Large Language Models (LLMs) and transformer architectures have shown impressive reasoning and generation capabilities across diverse natural language tasks. However, their reliability and robustness in real-world engineering domains remain largely unexplored, limiting their practical utility in human-centric workflows. In this work, we investigate the applicability and consistency of LLMs for analog circuit design -- a task requiring domain-specific reasoning, adherence to physical constraints, and structured representations -- focusing on AI-assisted design where humans remain in the loop. We study how different data representations influence model behavior and compare smaller models (e.g., T5, GPT-2) with larger foundation models (e.g., Mistral-7B, GPT-oss-20B) under varying training conditions. Our results highlight key reliability challenges, including sensitivity to data format, instability in generated designs, and limited generalization to unseen circuit configurations. These findings provide early evidence on the limits and potential of LLMs as tools to enhance human capabilities in complex engineering tasks, offering insights into designing reliable, deployable foundation models for structured, real-world applications.
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。