AgentNativeResearchLab/arc-agi3-grok-4.5-ar25 download history

AgentNativeResearchLab/arc-agi3-grok-4.5-ar25 is a reinforcement learning dataset on the Hugging Face Hub. In the last 30 days it was downloaded 448 times (73 in the last 7 days), and 960 times in total. It ranks #36,123 among datasets by monthly downloads.

ARC-AGI-3 ar25 — Agent Trajectories (grok-4.5) Gameplay trajectories from the harness×model pair grok-4.5 playing the ARC-AGI-3 game ar25, part of the ARA-as-world-model generalization experiment. The agent builds a structured world model (an Agent-Native Research Artifact) live durin

Open AgentNativeResearchLab/arc-agi3-grok-4.5-ar25 on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.