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 Artifact) live during play and consults it to crack levels it
cannot solve from cold exploration. Companion dataset:
arc-agi3-ls20-agent-trajectories.
Synced continuously during play — every… See the full description on the dataset page:
https://huggingface.co/datasets/AgentNativeResearchLab/arc-agi3-su15-agent-trajectories.
