BDH-CQ：结合循环潜在推理的上下文学习新方法

AI 摘要

Hugging Face 每日论文介绍了一项名为 BDH-CQ 的研究，该研究将上下文学习与循环潜在推理相结合，提出了一种 150M 参数的推理模型。该模型在 ARC-AGI-1 基准上达到了 29.5% 的 pass@2 准确率，每任务推理成本仅为 0.0007 美元，突破了该基准的成本-精度帕累托前沿，树立了新的成本效率标杆。

正文节选

BDH-CQ: In-Context Learning with Recurrent Latent Reasoning Abstract A 150M-parameter reasoning model using recurrent latent reasoning and in-context learning achieves a new cost-accuracy frontier on ARC-AGI-1. 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, wi

发布时间：—

抓取时间：2026-08-12 01:41

来源机构：Hugging Face