# NVIDIA's SpatialClaw Uses Code as the Action Interface for Spatial Reasoning

A training-free framework lets a vision-language agent write and run Python to compose perception steps and inspect intermediate results.

- Published: 2026-07-02T10:40:43.833Z
- Canonical: https://polylog.news/ai/2026-07-02/nvidia-s-spatialclaw-uses-code-as-the-action-interface-for-s
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Polylog editors](https://polylog.news)

NVIDIA researchers introduced SpatialClaw, described as a training-free framework for spatial reasoning that treats code as the interface for action. Rather than fine-tuning a model for spatial tasks, the approach lets a vision-language mod…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-07-02/nvidia-s-spatialclaw-uses-code-as-the-action-interface-for-s (subscription information: https://polylog.news/pricing).