🛰️ Daily AI Frontier
‹ back to 2026-08-11

BDH-CQ: In-Context Learning with Recurrent Latent Reasoning

Research LLMs & Foundation Models

Ranking

Overall 81
Content 85
Popularity 70

Observed public metrics from 1 member.

Representative image for BDH-CQ: In-Context Learning with Recurrent Latent Reasoning

Merged summary

TL;DR - BDH-CQ is a reasoning model that folds in-context demonstrations into a recurrent memory and then solves queries via iterative computation in latent space, reaching 29.5% pass@2 on ARC-AGI-1 at $0.0007 per task. It matters because it claims a new state of the art on the ARC-AGI-1 cost-accuracy Pareto frontier with only 150M parameters.

  • Combines in-context learning with recurrent latent reasoning: inference-time inputs continuously update recurrent memory, and the query is solved by iterating in a high-dimensional latent space rather than emitting verbalized chain-of-thought.
  • Evaluated on the public ARC-AGI-1 evaluation set; a 150M-parameter configuration reports 29.5% pass@2 at a computed inference cost of $0.0007 per task.
  • The authors position this operating point as breaking the previously reported ARC-AGI-1 cost-accuracy Pareto frontier — the headline claim is benchmark cost efficiency, not raw accuracy.
  • Controlled ARC-like interventions are used as analysis probes: what the model extracts from demonstrations, how consistently it applies an inferred transformation, and which concepts remain hard.

Sources (1)

BDH-CQ: In-Context Learning with Recurrent Latent Reasoning

arXiv cs.NE Björn Engdahl, Adrian Kosowski, Jan Chorowski, Zuzanna Stamirowska, Przemysław Uznański, Junlin Jiang, Rohan Phadke, Remigiusz Kinas, Richard Zhong 2026-08-10 arXiv:2608.09888
Public signals Hugging Face upvotes 779
Providers: Hugging Face · Upvotes 779 OpenAlex · N/A Publisher · N/A Semantic Scholar · N/A X · N/A Fetched 2026-09-10 14:31:29.289388 UTC

TL;DR - BDH-CQ is a reasoning model that folds in-context demonstrations into a recurrent memory and then solves queries via iterative computation in latent space, reaching 29.5% pass@2 on ARC-AGI-1 at $0.0007 per task. It matters because it claims a new state of the art on the ARC-AGI-1 cost-accuracy Pareto frontier with only 150M parameters.

  • Combines in-context learning with recurrent latent reasoning: inference-time inputs continuously update recurrent memory, and the query is solved by iterating in a high-dimensional latent space rather than emitting verbalized chain-of-thought.
  • Evaluated on the public ARC-AGI-1 evaluation set; a 150M-parameter configuration reports 29.5% pass@2 at a computed inference cost of $0.0007 per task.
  • The authors position this operating point as breaking the previously reported ARC-AGI-1 cost-accuracy Pareto frontier — the headline claim is benchmark cost efficiency, not raw accuracy.
  • Controlled ARC-like interventions are used as analysis probes: what the model extracts from demonstrations, how consistently it applies an inferred transformation, and which concepts remain hard.
item →