@HuggingPapers: SpatialClaw NVIDIA drops a training-free spatial reasoning agent that uses code as its action interface. A VLM writes P…
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.
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
SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning
SpatialClaw is a training-free framework that uses code as an action interface to enable flexible, stateful spatial reasoning in vision-language models, achieving superior performance across diverse 3D/4D spatial reasoning tasks.
@dair_ai: https://x.com/dair_ai/status/2068724104815890889
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…
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.
VisualClaw: A Real-Time, Personalized Agent for the Physical World
VisualClaw is a self-evolving multimodal agent that reduces deployment costs through hybrid encoding and skill evolution, while improving video-QA accuracy across multiple benchmarks.
SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes
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.