AgentNativeResearchLab/arc-agi3-kimi-k2.7-su15 download history

AgentNativeResearchLab/arc-agi3-kimi-k2.7-su15 is a reinforcement learning dataset on the Hugging Face Hub. In the last 30 days it was downloaded 4,221 times (687 in the last 7 days), and 5,543 times in total. It ranks #6,505 among datasets by monthly downloads.

ARC-AGI-3 su15 — Agent Trajectories (kimi-k2.7) Gameplay trajectories from the harness×model pair kimi-k2.7 playing the ARC-AGI-3 game su15, 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-kimi-k2.7-su15 on Hugging Face