发表机构
Duke University; MIT-IBM Watson AI Lab; IBM T. J. Watson Research Center（杜克大学; 麻省理工学院-IBM沃森人工智能实验室; IBM T. J. 沃森研究中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对自动化模拟电路拓扑设计难题，提出EXPLORE框架，集成模拟器引导蒙特卡罗树搜索与基于变压器的解码，利用语言模型先验优化搜索，在6组件基准测试中显著提升成功率、降低均方误差，推动LLM驱动设计自动化。
AI 中文摘要
自动化模拟电路拓扑设计对于减少满足日益多样化和定制化应用需求所需的大量人工工作至关重要。最近的进展是在预训练语言模型上应用序列到序列微调，以单次从用户规范直接生成电路拓扑。然而，由于搜索空间呈指数增长且训练数据集有限，这些一次性生成方法无法生成复杂电路。本文提出了EXPLORE，这是一个搜索增强框架，它将模拟器引导的蒙特卡罗树搜索（MCTS）与基于变压器的解码相结合，以实现模拟拓扑生成的测试时扩展。通过利用语言模型先验并绕过高置信度结构令牌，EXPLORE在搜索过程中将昂贵的模拟器预算主要分配给改变拓扑的决策。在公差为0.01的6组件基准测试中，EXPLORE将一次性生成的成功率从12%和采样与过滤基线的33%提高到65%，并在相同搜索预算下相对于采样与过滤将均方误差降低了20%以上。这些结果使EXPLORE成为第一个将结构化测试时搜索与LM解码集成用于模拟拓扑生成的框架，也是迈向扩展LLM驱动设计自动化的实际一步。
英文摘要
Automating analog circuit topology design is essential to reduce the extensive manual effort required to meet increasingly diverse and customized application demands. Recent advances have applied sequence-to-sequence fine-tuning on pretrained language models to directly generate circuit topologies from user specifications in a single pass. However, these one-shot generation methods failed to generate complex circuits due to their exponentially growing search spaces and limited training datasets. In this paper, we present EXPLORE, a search-enhanced framework that integrates simulator-guided Monte Carlo Tree Search (MCTS) with transformer-based decoding to enable test-time scaling for analog topology generation. By leveraging language-model priors and bypassing high-confidence structural tokens, EXPLORE allocates expensive simulator budget primarily toward topology-altering decisions during search. On a 6-component benchmark at a tight tolerance of 0.01, EXPLORE raises the success rate from 12% for one-shot generation and 33% for a sampling-and-filter baseline to 65%, and lowers MSE by over 20% relative to sampling-and-filter under the same search budget. These results establish EXPLORE as the first framework to integrate structured test-time search with LM decoding for analog topology generation, and a practical step toward scaling LLM-driven design automation.
CommentsMLCAD 26' accepted
