**VABench: Measuring Embodied Spatial Intelligence through Visual Demonstrations, Active Perception, and Metric Control**

> Spatial intelligence requires more than describing object locations. Under incomplete observation, models must identify and acquire missing evidence, interpret it in a common spatial frame, and act on it. We introduce VA-Bench to evaluate the complete observe-reason-act-revise loop. General-purpose MLLMs learn procedural context from RGB-only demonstrations, actively select camera viewpoints, issue metric Cartesian c...

**来源信息**
- **来源**：HuggingFace Daily Papers（社区热门论文）
- **分类**：ai-models
- **发布时间**：2026-09-18 08:00（北京时间）
- **原文**：[打开原文](https://huggingface.co/papers/2609.19554)