RFBench:面向无源 RF 版图设计与理解的多模态仿真基准发布
RFBench: A Simulator-Grounded Multimodal Benchmark for Passive RF Layout Design and Understanding
AI 导读
研究者推出 RFBench,一个基于 ADS Momentum 仿真、面向无源射频(RF)版图设计与理解的多模态数据集和基准。数据集包含 10,000 个二端口平面版图,每条样本含可编辑几何图元、栅格图像、16x16 占用网格、201 个频点的复数 S 参数、结构类别和 RF 响应标签,并定义了版图生成、响应预测、设计诊断等七项任务。
正文 · 原文
Abstract:While multimodal language models can interpret diagrams and generate structured outputs, their capacity to connect passive radio-frequency (RF) design intent, layout geometry, and electromagnetic behavior remains largely untested. To address this gap, we introduce RFBench, a simulator-grounded dataset and benchmark for passive RF layout design and understanding. The dataset contains 10,000 two-port planar layouts simulated using ADS Momentum, with each layout represented by editable geometric primitives, a raster image, a 16x16 occupancy grid, complex S-parameters at 201 frequency points, a structural category, and an RF response label. Building on these aligned representations, we define seven tasks spanning specification-conditioned layout generation, representation translation, response prediction, simulator-based validation, design diagnosis and improvement, structural understanding, and response classification. Extensive baselines across seven multimodal language models reveal systematic weaknesses in generating structurally valid layouts and predicting electromagnetically faithful responses. We show that RF-specific fine-tuning increases T1a structural validity from 0.0% to 83.2% and the T3 primitive-input within-2-dB rate from 17.7% to 62.8%, demonstrating the value of domain adaptation while leaving considerable room for further progress. RFBench establishes a common testbed for evaluating multimodal RF capabilities and guiding the development of models that connect design intent and layout representations with physical behavior.
| Comments: | 29 pages, 4 figures. Code: this https URL . Data: this https URL |
| Subjects: | Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.23410 [cs.AI] |
| (or arXiv:2611.23410v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.23410 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jiarui Cui [view email]
[v1]
Tue, 17 Nov 2026 19:10:14 UTC (797 KB)
来源:arXiv cs.AI · arxiv.org