Learning Layer Paper Reading Club - Week 28 - BDH-CQ: In-Context Learning with Recurrent Latent Reasoning
This week's paper: BDH-CQ: In-Context Learning with Recurrent Latent Reasoning
Link: https://arxiv.org/abs/2608.09888
Abstract: We introduce BDH-CQ, a reasoning model that combines in-context learning with recurrent latent reasoning. Inputs presented at inference time continuously update the model's recurrent memory; the model then solves a query through iterative computation in a high-dimensional latent space, without verbalizing its intermediate reasoning. We evaluate the model on the public ARC-AGI-1 evaluation set and use controlled ARC-like interventions to study what it learns from demonstrations, how consistently it applies an inferred transformation, and which concepts remain difficult. A 150M-parameter configuration reaches 29.5% pass@2 at a computed inference cost of $0.0007 per task. This operating point breaks through the previously reported ARC-AGI-1 cost-accuracy Pareto frontier, establishing a new state of the art in benchmark cost efficiency.
Want to train your own on your own laptop? Clone the repo with Claude Code and say "Let's do it!" https://github.com/doomdagadiggiedahdah/bdh-tinystories
What is the Learning Layer Labs Paper Reading Club?
An initiative from https://www.learninglayer.ai, a lab with the goal of reducing AI anxiety in the world.
What is the format?
Discussion based. Expect a low pressure environment to share insights and opinions with the group.
What are the group goals?
Stay on top of AI research and improve understanding of AI fundamentals + math.
Who is welcome?
Everyone! Try to put in at least some time on the paper and come prepared with questions or things you'd like to discuss, but it's ok to just show up!
Learning Layer Labs team:
Thomas Redfern ( The backbone who runs every paper reading )
Mat Allen (The new fella bring order and organization)
Devinder Sodhi (The guy you talk to for sponsoring)
Hanwha AI Center (HAC) is hosting us this week!
About HAC
Hanwha AI Center (HAC) is a private membership for all those dedicated to AI. As a hub for innovation, HAC brings together passionate entrepreneurs, researchers, and visionaries to explore the societal and technological impacts of AI on human life.