RoboSpatial

SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RL

arXiv:2512.04069v2 Announce Type: replace Abstract: Vision Language Models (VLMs) demonstrate strong qualitative visual understanding, but struggle with metrically precise spatial reasoning required for embodied applications. The agentic paradigm promises that VLMs can use a wide variety of tools that could augment these capabilities, such as depth estimators, segmentation models, and pose estimators. Yet it remains an open challenge how to realize this vision without solely relying on...