Continual-ARC

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

Prime Agent, told to keep a program library

Told to keep one tested program per task and run it first when the task returns.

Stream, budget used
8.2 solved 99%
Epilogue, budget used
19.3 solved 96%
Model spend
$1.62 2,132 calls
Instances
225 5.8 hours

Budget used is the share of the cap of 16 that an instance used, averaged over the instances: a wrong answer and a demonstration each cost 1, so lower is better.

Loading the run