Continual-ARC

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

Hermes 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
34.4 solved 76%
Epilogue, budget used
40.8 solved 64%
Model spend
$12.96 18,328 calls
Instances
225 14.3 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