SpatialClaw Accepted to NeurIPS 2026: Free Code-Action Harness Lifts Frontier Models Up to 15 Points on 20 Spatial Benchmarks

CMHungSteven · x · 2026-09-29

SpatialClaw is accepted to NeurIPS 2026. The training-free, model-agnostic harness — a persistent Python kernel where the VLM writes one cell per step, inspects SAM/depth/geometry outputs, revises, then answers — lifts four frontier models across 20 spatial benchmarks:

Notably, even GPT-6 Astra, which already looks "spatial," improves with the kernel — showing the action interface itself remains a lever. Paper, code and website are public.

Related event: SpatialClaw Accepted to NeurIPS 2026, Boosting Spatial Reasoning by up to 15 Points(2 posts)→

Original post →

More from Research

Research channel →