Continual-ARCby unify

ReplayARC-AGI-1 · Fresh · GPT-6 Luna, medium

Hermes Agent, asked to store

Asked after every verdict to store what would help next time.

Held-out tasks, budget used
28.5 solved 89%
Model spend
$4.12 6,488 calls
Instances
100 9.9 hours

Budget used is the share of the cap of 16 that an instance was charged, averaged over the instances: a solved instance costs 1 for each wrong answer and each demonstration, an unsolved one all 16, so lower is better.

Loading the run