Problem
Research questions and friction points this paper is trying to address.
turbomachinery CFD
natural language intents
visualization procedures
multi-agent workflow
structured representation
CATVis: A Collaborative Multi-Agent Workflow for Turbomachinery Simulation Data Visualization
🤖 AI Summary
为解决涡轮机械CFD后处理中目标模糊的问题，CATVis通过多代理协作将自然语言意图转化为可视化流程，提高生成准确性。
📝 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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Collaborative Multi-Agent
Natural Language Interface
Turbomachinery CFD
Workflow Generation
Visualization
🔎 Similar Papers
No similar papers found.
