@HuggingPapers: SpatialClaw NVIDIA drops a training-free spatial reasoning agent that uses code as its action interface. A VLM writes P…

X AI KOLs Following Papers

Summary

NVIDIA introduces SpatialClaw, a training-free spatial reasoning agent that uses a VLM to write Python code in a persistent kernel, compose perception tools, and revise plans, achieving +11.2 points over prior agents on 20 benchmarks.

SpatialClaw NVIDIA drops a training-free spatial reasoning agent that uses code as its action interface. A VLM writes Python in a persistent kernel, composes perception tools, inspects results, and revises its plan—no fine-tuning needed. +11.2 points over prior agents on 20 https://t.co/MJH98obV52
Original Article
View Cached Full Text

Cached at: 06/17/26, 07:58 PM

SpatialClaw

NVIDIA drops a training-free spatial reasoning agent that uses code as its action interface. A VLM writes Python in a persistent kernel, composes perception tools, inspects results, and revises its plan—no fine-tuning needed. +11.2 points over prior agents on 20 https://t.co/MJH98obV52

Similar Articles

@dair_ai: https://x.com/dair_ai/status/2068724104815890889

X AI KOLs Following

Highlights three recent AI papers: SpatialClaw (training-free spatial reasoning via code), SkillWeaver (compositional skill routing with decompose-retrieve-compose pipeline), and PreAct (compiling agent runs into fast state machines for repeated tasks).

@Phoenixyin13: NVIDIA's SpatialClaw is fresh out. This framework directly lets VLM write code step by step in a persistent Python environment, like Jupyter. From calling SAM3 to see things, compute depth, use NumPy and SciPy to process data, view results in real time, if it doesn't work…

X AI KOLs Timeline

NVIDIA has launched SpatialClaw, a code-based training-free agent framework for complex visual-spatial reasoning tasks, achieving an average of 59.9% on 20 benchmarks, 11.2 points higher than the previous best model.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes

Hugging Face Daily Papers

SpatialAct is a new simulator-grounded benchmark that probes whether VLM agents can perform coherent spatial reasoning and translate it into actions in 3D environments across multi-turn feedback settings. Experiments reveal a significant reasoning-to-action gap, with current VLMs struggling to maintain spatial beliefs and produce reliable actions despite performing well on isolated reasoning tasks.