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

arXiv: https://arxiv.org/abs/2601.07315 · HTML: https://mlsanity.com/paper/2601.07315/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 19 of its 50 references that are in the map.
- First posted on arXiv 12 Jan 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- Multimodal LLMs / vision-language models / [Chart understanding and anomaly detection](https://mlsanity.com/mllm/chart-understanding-and-anomaly-detection/)
- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 19 of 19)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Scalable Global Optimization via Local Bayesian Optimization](https://mlsanity.com/paper/1910.01739/) (2019)
- [Vision language models are blind: Failing to translate detailed visual features into words](https://mlsanity.com/paper/2407.06581/) (2024)
- [On the Robustness of Large Multimodal Models Against Image Adversarial Attacks](https://mlsanity.com/paper/2312.03777/) (2023)
- [HalluLens: LLM Hallucination Benchmark](https://mlsanity.com/paper/2504.17550/) (2025)
- [Vision Language Models are Biased](https://mlsanity.com/paper/2505.23941/) (2025)
- [AutoCkt: Deep Reinforcement Learning of Analog Circuit Designs](https://mlsanity.com/paper/2001.01808/) (2020)
- [Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Spatial Reasoning](https://mlsanity.com/paper/2410.16162/) (2024)
- [AmpAgent: An LLM-based Multi-Agent System for Multi-stage Amplifier Schematic Design from Literature for Process and Performance Porting](https://mlsanity.com/paper/2409.14739/) (2024)
- [AMSNet: Netlist Dataset for AMS Circuits](https://mlsanity.com/paper/2405.09045/) (2024)
- [LEDRO: LLM-Enhanced Design Space Reduction and Optimization for Analog Circuits](https://mlsanity.com/paper/2411.12930/) (2024)
- [EEsizer: LLM-Based AI Agent for Sizing of Analog and Mixed Signal Circuit](https://mlsanity.com/paper/2509.25510/) (2025)
- [CIRCUIT: A Benchmark for Circuit Interpretation and Reasoning Capabilities of LLMs](https://mlsanity.com/paper/2502.07980/) (2025)
- [AnaFlow: Agentic LLM-based Workflow for Reasoning-Driven Explainable and Sample-Efficient Analog Circuit Sizing](https://mlsanity.com/paper/2511.03697/) (2025)
- [MAPS: Advancing Multi-Modal Reasoning in Expert-Level Physical Science](https://mlsanity.com/paper/2501.10768/) (2025)
- [AnalogGym: An Open and Practical Testing Suite for Analog Circuit Synthesis](https://mlsanity.com/paper/2409.08534/) (2024)
- [ChartHal: A Fine-grained Framework Evaluating Hallucination of Large Vision Language Models in Chart Understanding](https://mlsanity.com/paper/2509.17481/) (2025)
- [Emerging ML-AI Techniques for Analog and RF EDA](https://mlsanity.com/paper/2506.00007/) (2025)

## Abstract (arXiv)

Vision Language Models (VLMs) have demonstrated remarkable potential in multimodal reasoning. However, they can have 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 to support 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 employs agent-generated semantic seeds to warm-start local searches and uses Automatic Relevance Determination to provide sensitivity evidence for the final design report. Experimental results on 12 sizing tasks covering six circuits and four technology platforms show that VLM-CAD achieves a pooled Strict Pass@1 of 23.3% and a Relaxed Pass@1 of 91.7%, while providing sensitivity evidence for final design reports.