SOURCE-LINKED INTELLIGENCE

Selective Tool Use for Agentic Change Visual Question Answering in Remote Sensing

arXiv · AI, language, vision and robotics · article · Sep 13, 2026 · UTC

Change visual question answering (Change VQA) requires understanding semantic changes across bi-temporal remote sensing images. Although vision language models (VLMs) have shown promising performance on this task, they remain unreliable when answering questions that require explicit transition statistics, area measurements, or spatial information. To address this limitation, we propose a selective tool use framework in which a single VLM either answers directly or invokes a deterministic change analysis tool to obtain question specific evidence. Specifically, the selected tool operates on bi-t

Read original source ↗ Open in workspace

recordType

paper

region

Global