Agent Farah
A very simple ARC AGI 3 solver agent based on existing approach.
Core trick
Runs an LLM loop that infers game rules from grid observations, takes actions, and scores each level with the RHAE action-efficiency formula.
Description
A very simple ARC AGI 3 solver agent based on existing approach. ARC-AGI-3 is a turn-based games on a 64×64 grid where the rules are never given; the agent must figure out how to play and clear levels. The evaluation uses RHAE metric (Relative Human Action Efficiency: per level min((human_actions / ai_actions)², 1.15), averaged over games).
The linked repo returns 404, so it was deleted or made private.