AgentNativeResearchLab/arc-agi3-agy-gemini3.1pro-g50t download history

AgentNativeResearchLab/arc-agi3-agy-gemini3.1pro-g50t is a reinforcement learning dataset on the Hugging Face Hub. In the last 30 days it was downloaded 795 times (235 in the last 7 days), and 1,400 times in total. It ranks #23,015 among datasets by monthly downloads.

ARC-AGI-3 g50t — Agent Trajectories (agy-gemini3.1pro) Gameplay trajectories from the harness×model pair agy-gemini3.1pro playing the ARC-AGI-3 game g50t, part of the ARA-as-world-model generalization experiment. The agent builds a structured world model (an Agent-Native Research Arti

Open AgentNativeResearchLab/arc-agi3-agy-gemini3.1pro-g50t on Hugging Face