AI RESEARCH
Exploring Interaction Paradigms for LLM Agents in Scientific Visualization
arXiv CS.AI
•
ArXi:2604.27996v1 Announce Type: new This paper examines how different types of large language model (LLM) agents perform on scientific visualization (SciVis) tasks, where users generate visualization workflows from natural-language instructions. We compare three primary interaction paradigms, including domain-specific agents with structured tool use, computer-use agents, and general-purpose coding agents, by evaluating eight representative agents across 15 benchmark tasks and measuring visualization quality, efficiency, robustness, and computational cost.