Recurrent latent reasoning pushes 150M model to a new ARC-AGI cost frontier
BDH-CQ solves queries by updating a recurrent memory from in-context demonstrations and computing in high-dimensional latent space, never parameter updates or verbalized reasoning. At 150M params it hits 29.5% pass@2 on ARC-AGI-1 at $0.0007 per task, breaking the benchmark's cost-accuracy Pareto frontier.