AnalogScout：基于 LLM 智能体的仿真高效 PVT 感知模拟电路尺寸优化框架
AnalogScout: Simulation-Efficient PVT-Aware Analog Sizing with LLM Agents
AI 导读
AnalogScout 是一个由 LLM 智能体驱动的仿真高效 PVT 感知模拟电路尺寸优化框架，结合精英设计复用、解析 gm/Id 局部定尺寸和全工艺角验证下的全局精调。在三个 SKY130 OTA 上、同样 16k 次仿真的预算下，功耗较演化策略 CMA-ES 降低 43.3%，且仅用其 7.0% 预算即达到 CMA-ES 的最终功耗；功耗还低于贝叶斯优化及两个复现的 LLM 驱动流程。
正文 · 原文
Abstract:Analog device sizing must satisfy all specifications across process, voltage, and temperature (PVT) corners to ensure tape-out success, but simulating every candidate at all corners dominates the sizing time and slows design iteration. Conventional surrogate-based optimizers search the sizing space directly, while recent large language model (LLM) agents add circuit knowledge to designs but still delegate the sizes to global optimizers. Both learn the circuit response from repeated multi-corner SPICE simulations and optimize on top of it, which becomes expensive under a limited simulation budget. Providing an agent with reusable verified designs and sizing sub-blocks analytically could save most of this budget. We propose AnalogScout, a simulation-efficient PVT-aware sizing framework driven by an LLM agent. Combining elite-design reuse, analytic gm/Id local sizing and global refinement under full-corner verification, AnalogScout reduces power by 43.3% relative to the evolution strategy CMA-ES at an equal budget of 16k simulations on three SKY130 OTAs of increasing complexity, and reaches the final CMA-ES power after 7.0% of that budget. It also attains lower power than Bayesian optimization on all three OTAs and than two re-implemented LLM-driven flows on the two OTAs where they were tested.
| Comments: | 5 pages, 5 figures, 1 table. Submitted to IEEE ISCAS 2027 |
| Subjects: | Hardware Architecture (cs.AR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.37319 [cs.AR] |
| (or arXiv:2610.37319v1 [cs.AR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.37319 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yichen Long [view email]
[v1]
Tue, 27 Oct 2026 14:33:02 UTC (119 KB)
来源：arXiv cs.AI · arxiv.org