研究人员开发了BDH-CQ，一种将具身上下文学习与循环潜在推理相结合的新型推理模型。该模型使用推理时输入更新其记忆，并在潜在空间中迭代计算解决方案，而不对中间步骤进行口头表达。BDH-CQ在ARC-AGI-1基准测试中实现了成本效率新的最先进水平，其1.5亿参数配置在每任务成本为0.0007美元的情况下，pass@2达到了29.5%。 AI
影响 为AI推理确立了新的成本效率前沿，可能使更先进的AI能力更加普及。
排序理由 该集群描述了一篇关于新型AI模型及其在基准测试中表现的详细研究论文。
在 arXiv cs.NE (Neural & Evolutionary) 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
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 …
A 150M-parameter reasoning model using recurrent latent reasoning and in-context learning achieves a new cost-accuracy frontier on ARC-AGI-1.
arXiv:2608.09888v1 Announce Type: cross 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 i…