Tag
A 150M-parameter non-transformer architecture achieves state-of-the-art cost-efficiency on ARC-AGI-1, validated by Transformer co-author Łukasz Kaiser, suggesting that recurrent latent reasoning can replace brute-force scaling.
This paper introduces BDH-CQ, a 150M-parameter reasoning model that combines in-context learning with recurrent latent reasoning, achieving 29.5% pass@2 on ARC-AGI-1 at very low inference cost and establishing a new cost-accuracy frontier.