AgentNativeResearchLab/arc-agi3-su15-agent-trajectories download history

AgentNativeResearchLab/arc-agi3-su15-agent-trajectories is a reinforcement learning dataset on the Hugging Face Hub. In the last 30 days it was downloaded 499 times (151 in the last 7 days), and 4,376 times in total. It ranks #33,178 among datasets by monthly downloads.

ARC-AGI-3 su15 — Agent Trajectories Gameplay trajectories from an LLM agent (Claude Code driving a file-relay harness) 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 Artifac

Open AgentNativeResearchLab/arc-agi3-su15-agent-trajectories on Hugging Face