AgentNativeResearchLab/arc-agi3-cc-fable5-ar25 download history

AgentNativeResearchLab/arc-agi3-cc-fable5-ar25 is a reinforcement learning dataset on the Hugging Face Hub. In the last 30 days it was downloaded 527 times (143 in the last 7 days), and 1,370 times in total. It ranks #31,827 among datasets by monthly downloads.

ARC-AGI-3 ar25 — Agent Trajectories (cc-fable5) Gameplay trajectories from the harness×model pair cc-fable5 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 dur

Open AgentNativeResearchLab/arc-agi3-cc-fable5-ar25 on Hugging Face