SOURCE-LINKED INTELLIGENCE

WidgetVA: A Widget-Centric Framework and Benchmark for Agentic Visual Analytics

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

Visual analytics (VA) enables sensemaking through interactive visualization, but effective analysis often requires experts to translate high-level intents into long sequences of interface operations and iteratively interpret visual feedback. We study whether modern vision-language models (VLMs) can take on this role as autonomous VA operators that observe the interface, plan multi-step exploration, execute interactions, and adapt based on intermediate visual feedback. To support systematic development and evaluation, we first introduce WidgetVA, a widget-centric agentic VA framework that stand

Read original source ↗ Open in workspace

recordType

paper

region

Global