Continual-ARC

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

Hermes Agent, asked to store

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

Stream, budget used
41.2 solved 71%
Epilogue, budget used
54.5 solved 44%
Model spend
$8.23 12,495 calls
Instances
225 10.8 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