AgentNativeResearchLab/arc-agi3-codex-gpt5.6sol-r11l download history

AgentNativeResearchLab/arc-agi3-codex-gpt5.6sol-r11l is a reinforcement learning dataset on the Hugging Face Hub. In the last 30 days it was downloaded 843 times (151 in the last 7 days), and 2,897 times in total. It ranks #21,979 among datasets by monthly downloads.

ARC-AGI-3 r11l — Agent Trajectories (codex-gpt5.6sol) Gameplay trajectories from the harness×model pair codex-gpt5.6sol playing the ARC-AGI-3 game r11l, part of the ARA-as-world-model generalization experiment. The agent builds a structured world model (an Agent-Native Research Artifa

Open AgentNativeResearchLab/arc-agi3-codex-gpt5.6sol-r11l on Hugging Face

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