通过渐进式块大小训练，让扩散模型实现长链条推理。
DreamReasoner-8B: Block-Size Curriculum Learning for Diffusion Reasoning Models
- 采用渐进式块大小训练策略，解决大块推理时性能下降问题。
- 在数学与代码推理任务上表现媲美Qwen3-8B等自回归模型。
- 适合需要高效且强推理能力的扩散模型研究者使用。
块扩散语言模型通过并行块级去噪加速解码，但其在长链式思维（CoT）推理中的可扩展性尚未明确。为此，我们开发了开源的DreamReasoner-8B块扩散推理模型，并系统研究了训练与推理块大小对长CoT推理的影响。分析显示：以大块大小训练会导致推理性能显著下降，而小块大小则能保持有效推理。为弥合这一粒度差距，我们提出块大小课程学习，逐步从细粒度过渡到粗粒度块大小训练，从而克服该限制，实现跨多种推理块大小的强推理性能。在数学与代码推理基准上，DreamReasoner-8B的表现可与领先开源自回归模型Qwen3-8B相媲美。本工作为高效、具备推理能力的扩散语言模型奠定了实用基础。模型已开源至https://github.com/DreamLM/DreamReasoner。
原文摘要 · Abstract (English)
Block diffusion language models accelerate decoding through parallel block-wise denoising, yet whether they can be reliably scaled for long chain-of-thought (CoT) reasoning remains unresolved. To this end, we develop DreamReasoner-8B, an open-source block diffusion reasoning model, and conduct a systematic study of how training and inference block sizes affect long-CoT reasoning. Our analysis reveals a stark performance disparity: training with large block sizes yields remarkably poor reasoning, whereas small block sizes preserve effective reasoning. To bridge this granularity gap, we propose block-size curriculum learning, which gradually transitions training from fine-grained to coarse-grained block sizes, thereby overcoming this limitation and enabling strong reasoning performance that generalizes across diverse inference block sizes. On mathematical and code reasoning benchmarks, DreamReasoner-8B achieves results competitive with leading open autoregressive models such as Qwen3-8B. This work establishes a practical foundation for efficient, reasoning-capable diffusion language models. We release our model at https://github.com/DreamLM/DreamReasoner.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。