paper-with-me

홈 › Papers

VLM-CAD: VLM-Optimized Collaborative Agent Design Workflow for Analog Circuit Sizing

2026-01-12 · Guanyuan Pan, Shuai Wang, Yugui Lin, Tiansheng Zhou, Pietro Liò, Zhenxin Zhao, Yaqi Wang arxiv

Vision Language Models (VLMs) have demonstrated remarkable potential in multimodal reasoning, yet they inherently suffer from spatial blindness and logical hallucinations when interpreting densely structured engineering content, such as analog circuit schematics. To address these challenges, we propose a Vision Language Model-Optimized Collaborative Agent Design Workflow for Analog Circuit Sizing (VLM-CAD) designed for robust, step-by-step reasoning over multimodal evidence. VLM-CAD bridges the modality gap by integrating a neuro-symbolic structural parsing module, Image2Net, which transforms raw pixels into explicit topological graphs and structured JSON representations to anchor VLM interpretation in deterministic facts. To ensure the reliability required for engineering decisions, we further propose ExTuRBO, an Explainable Trust Region Bayesian Optimization method. ExTuRBO serves as an explainable grounding engine, employing agent-generated semantic seeds to warm-start local searches and utilizing Automatic Relevance Determination to provide quantified evidence for the VLM's decisions. Experimental results on two complex circuit benchmarks demonstrate that VLM-CAD significantly enhances spatial reasoning accuracy and maintains physics-based explainability. VLM-CAD consistently satisfies complex specification requirements while achieving low power consumption, with a total runtime under 66 minutes, marking a significant step toward robust, explainable multimodal reasoning in specialized technical domains.

📄 PDF Abstract BibTeX arXiv:2601.07315

Code (0)

등록된 구현이 없습니다.

Tasks

Multimodal ReasoningSpatial Reasoning

Similar Papers 제목 키워드 기반

MenTeR: A fully-automated Multi-agenT workflow for end-to-end RF/Analog Circuits Netlist Design

2025-05-29 · Pin-Han Chen, Yu-Sheng Lin, Wei-Cheng Lee, Tin-Yu Leu 외

RF/Analog design is essential for bridging digital technologies with real-world signals, ensuring the functionality and reliability of a wide range of electronic systems. However, analog design procedures are often intri…

ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems

2024-09-02 · CVPR 2025 1 · Xiangyuan Xue, Zeyu Lu, Di Huang, Zidong Wang 외

Much previous AI research has focused on developing monolithic models to maximize their intelligence, with the primary goal of enhancing performance on specific tasks. In contrast, this work attempts to study using LLM-b…

BenchmarkingInstruction Following

Multi-Agent Collaborative Filtering: Orchestrating Users and Items for Agentic Recommendations

2025-11-23 · Yu Xia, Sungchul Kim, Tong Yu, Ryan A. Rossi 외 arxiv

Agentic recommendations cast recommenders as large language model (LLM) agents that can plan, reason, use tools, and interact with users of varying preferences in web applications. However, most existing agentic recommen…

Collaborative Filtering

AgentCo-op: Retrieval-Based Synthesis of Interoperable Multi-Agent Workflows

2026-05-19 · Shuaike Shen, Wenduo Cheng, Shike Wang, Mingqian Ma 외 arxiv

Designing multi-agent workflows is especially difficult in open-ended scientific settings where tasks lack curated training sets, reliable scalar evaluation metrics, and standardized interfaces between existing tools and…

EvoMAS: Learning Execution-Time Workflows for Multi-Agent Systems

2026-05-09 · Chengdong Xu, Kaiqiang Ke, Ziheng Liu, Jiaqi Wei 외 arxiv

Large language model (LLM)-based multi-agent systems have shown strong potential on complex tasks through agent specialization, tool use, and collaborative reasoning. However, most automated multi-agent system design met…