NVIDIA's SpatialClaw: Code as Action Interface Boosts VLM Spatial Reasoning Training-Free, Accepted at NeurIPS

NVIDIA's paper SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning has been accepted at NeurIPS 2026. Its core claim is that code is the right action interface for spatial reasoning. The framework is training-free and model-agnostic, enabling VLMs to perform agentic 3D/4D spatial reasoning, delivering an average gain of about 11.2 points across 20 spatial reasoning benchmarks, with GPT-6 Astra reaching 71.3 and up to 15 points improvement for four frontier models.

Confirmed

Why it matters

2026-09-29 ~ 2026-09-30 · 5 related posts

Primary sources