@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 Papers

Summary

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.

NVIDIA's SpatialClaw is fresh out. This framework directly enables VLM to write code step by step in a persistent Python environment, like Jupyter. From calling SAM3 to see things, compute depth, use NumPy and SciPy for data processing, view results in real time, if it doesn't work then revise, and continue iterating — highly efficient. As a result, it averages 59.9% on 20 spatial reasoning benchmarks, 11.2 points higher than the previous strongest SpaceTools, especially excellent on complex tasks like multi-view, video, and 4D. “Code is the right action interface for spatial reasoning agents.” A truly flexible workbench that opens up a whole new world, letting you unleash your full potential.
Original Article
View Cached Full Text

Cached at: 06/17/26, 08:03 PM

NVIDIA’s SpatialClaw just dropped.

This framework lets VLM directly write code step by step in a persistent Python environment, like a slow-paced Jupyter. It starts by using SAM3 to see things, computes depth, processes data with NumPy and SciPy, views results in real time — if something’s off, just edit and iterate. Incredibly efficient.

As a result, the average score on 20 spatial reasoning benchmarks is 59.9%, a full 11.2 points higher than the previous best, SpaceTools — especially excelling on complex tasks like multi-view, video, and 4D.

“Code is the right action interface for spatial reasoning agents.”

A truly flexible workbench that opens up a new world, letting you push your limits to the max.

NVIDIA AI (@NVIDIAAI): Code is the right action interface for spatial reasoning agents.

New from NVIDIA Research: SpatialClaw, a training-free agent that uses code as its action interface for complex visual tasks.

Instead of calling a fixed set of pre-defined tools, the agent writes Python inside a

Similar Articles

@xiaogaifun: https://x.com/xiaogaifun/status/2073771786202939572

X AI KOLs Timeline

The ByteDance Seed team released the EdgeBench benchmark, which allows AI models to work continuously for 12-72 hours to evaluate their learning ability in long-horizon tasks. They discovered that the relationship between the time spent learning from the environment and performance follows a log-sigmoid curve, revealing a new scaling law.