Collaborative agents translate language to turbomachinery visualization workflows
CATVis: A Collaborative Multi-Agent Workflow for Turbomachinery Simulation Data Visualization
Human-Computer Interaction
Summary
Analyzing complex airflow and other effects inside turbomachinery devices can be difficult and requires specialized visualization tools. The authors created CATVis, a system where multiple AI agents work together to turn natural language requests, like 'find vortices,' into step-by-step visualization workflows. These workflows help engineers see and understand the data clearly. The system improves accuracy by breaking down the process into stages and refining the output using domain knowledge.
What this means in practice
- •For turbomachinery engineers: Create clear visualization workflows directly from natural language goals for analyzing CFD simulation data.
- •For industrial cfd analysts: Use a multi-agent system to improve the accuracy and reduce complexity when generating visualization procedures.
Authors
Zhe Wang, Zehao Lou, Guanghui Zhao, Yu Dong, Guan Li, Pengyi Xu, Gaorong Liang, Jun Liu, Guihua Shan
Abstract
Recent advances in AI for Science have enabled natural language (NL) interfaces for scientific data analysis. In turbomachinery CFD post-processing, translating ambiguous high-level analytical goals (e.g., vortex identification) into precise visualization procedures supporting complex domain-specific analysis is challenging. We present CATVis, a Collaborative multi-agent workflow system that bridges this gap by transforming NL intents into structured middle representation for visualization. Our approach reformulates domain-specific visualization procedures as composable workflow representations, and use multi agent to generate workflow representations via intent planning, template generation, and error-aware refinement, where each stage incrementally updates a shared structured representation. We evaluate the impact of external knowledge and workflow structuring on generation accuracy, demonstrating that the proposed approach significantly improves complex workflow generation correctness while reducing prompt complexity.