# Spatial Harness: Grounding Spatial Reasoning in Executable World States with Physics Engines > Source: > Published: 2026-11-10 10:00:08+00:00 Spatial reasoning requires understanding how objects and observers are arranged in a scene and how their relations change with viewpoint or movement. Vision-language models (VLMs) typically perform both steps through model-internal reasoning, forming an implicit scene interpretation from partial vie