Metraipolis › archive › dc_55adbfdb326e

BDH-CQ: In-Context Learning with Recurrent Latent Reasoning — arXiv:2608.09888

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.09888
License (as archived)
CC0-1.0
Archived
2026-10-19T09:02:52.709Z
SHA-256 of the archived text
2136017a58f247ea38aa3a45bef83328912e66abed8a31d939b992d755f84e03
Stable URL of this page
https://metraipolis.com/documento/dc_55adbfdb326e

How to cite

BDH-CQ: In-Context Learning with Recurrent Latent Reasoning — arXiv:2608.09888 — arXiv (en), https://arxiv.org/abs/2608.09888 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_55adbfdb326e (Metraipolis archive dc_55adbfdb326e, sha256 2136017a58f247ea38aa3a45bef83328912e66abed8a31d939b992d755f84e03)
BibTeX
@misc{dc55adbfdb326e,
  title = {BDH-CQ: In-Context Learning with Recurrent Latent Reasoning — arXiv:2608.09888},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.09888},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_55adbfdb326e; sha256 2136017a58f247ea38aa3a45bef83328912e66abed8a31d939b992d755f84e03},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.09888. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-11 in stat.ML).
Categorie arXiv: Neural and Evolutionary Computing (cs.NE) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2608.09888 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T09:01:32.163Z dalla pagina https://arxiv.org/catchup/stat.ML/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).