arXiv cs.AI· Vishal Saxena, Soumyajit Mandal·· 14 小时前AI 评分34
OPERA：由专家教学推理智能体完成从规格到版图的运放设计
OPERA: OPamp Design by an Expert-Taught Reasoning Agent, from Specifications to Layout
AI 导读
OPERA 让通用 LLM 智能体借助开源工具完成 CMOS 运放从规格到版图签核的全流程设计，先由设计师教会其 gm/ID 方法，再学习 gLayout 框架并编写可复用版图生成器。
正文 · 原文
Abstract:Analog flows from specifications to a signed-off layout rarely run without manual iteration. Recent large language model (LLM) agents size circuits with optimizer loops over the device dimensions and stop at the schematic. We present OPERA (OPamp design by an Expert-taught Reasoning Agent), in which a general-purpose LLM agent designs CMOS opamps from specifications to post-layout sign-off with open-source tools. First, the designer teaches the agent the gm/ID method: map the specifications to transconductances and minimum currents, choose gm/ID per device role from characterized lookup tables, and size from equations, leaving a few knobs to search and an explainable design. Second, the agent learns the gLayout framework and taught layout practice, and writes a reusable layout generator that closes the layout and extraction loop at designer-approved gates. In SKY130, the agent designed a shared constant-gm bias and six opamps (5T, folded-cascode and telescopic OTAs; Miller, folded-cascode and telescopic two-stage) for fun >= 50 MHz, PM >= 60 degrees, SR 25 V/{\mu}s into 1 pF and a minimum dc gain of 30 to 60 dB. All six layouts are DRC-clean and LVS-matched, and their extracted netlists meet every target at all 15 PVT corners ( fun >= 53.7 MHz, PM >= 62.1 degrees, SR >= 27.9 V/{\mu}s). The benchmark netlists are released at this https URL.
| Comments: | 5 pages, 3 figures, submitted to ISCAS 2027 |
| Subjects: | Hardware Architecture (cs.AR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.39395 [cs.AR] |
| (or arXiv:2610.39395v1 [cs.AR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.39395 arXiv-issued DOI via DataCite |
Submission history
From: Vishal Saxena [view email]
[v1]
Thu, 29 Oct 2026 05:29:47 UTC (1,711 KB)
来源：arXiv cs.AI · arxiv.org