mlsanityData to 14 Oct 2026

DreamReasoner-8B: Block-Size Curriculum Learning for Diffusion Reasoning Models

arXiv 2606.19257 ↗First posted 17 Jun 2026cs.CLcited by 5

On the map: LLM reasoning → Diffusion reasoning and test-time scaling

also in 1 more
Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Placed in Diffusion reasoning and test-time scaling, one of 17 directions in LLM reasoning. Builds on 44 of its 66 references that are in the map. First posted on arXiv 17 Jun 2026.

Builds on

44 of 66 references.

Closest ancestors · 2

Same direction, newest first

  1. 2026The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Models21 Jan
  2. 2025wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models7 Jul

Other references · 42

  1. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  2. 2025Qwen3 Technical Reportcited by 8,820
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  4. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  5. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  6. 2024Qwen2.5 Technical Reportcited by 4,942
  7. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  8. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,100
  9. 2021Program Synthesis with Large Language Modelscited by 3,637
  10. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  11. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 2,004
  12. 2019Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelismcited by 1,868
30 more
  1. 2024OpenAI o1 System Cardcited by 1,244
  2. 2025Large Language Diffusion Modelscited by 912
  3. 2017RACE: Large-scale ReAding Comprehension Dataset From Examinationscited by 861
  4. 2025Dream 7B: Diffusion Large Language Modelscited by 544
  5. 2026Kimi K2.5: Visual Agentic Intelligencecited by 501
  6. 2025Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decodingcited by 420
  7. 2025Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Modelscited by 409
  8. 2025LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Modelscited by 285
  9. 2024Scaling up Masked Diffusion Models on Textcited by 199
  10. 2025DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generationcited by 187
  11. 2024Flex Attention: A Programming Model for Generating Optimized Attention Kernelscited by 185
  12. 2025LLaDA2.0: Scaling Up Diffusion Language Models to 100Bcited by 166
  13. 2025Fast-dLLM v2: Efficient Block-Diffusion LLMcited by 139
  14. 2025SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generationcited by 129
  15. 2025Olmo 3cited by 129
  16. 2025MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttrainingcited by 121
  17. 2025Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoningcited by 104
  18. 2025Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Modelscited by 88
  19. 2025AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learningcited by 87
  20. 2025Dream-Coder 7B: An Open Diffusion Language Model for Codecited by 81
  21. 2025Diffusion Beats Autoregressive in Data-Constrained Settingscited by 63
  22. 2026LLaDA2.1: Speeding Up Text Diffusion via Token Editingcited by 54
  23. 2025Diffusion Language Models are Super Data Learnerscited by 48
  24. 2025SPG: Sandwiched Policy Gradient for Masked Diffusion Language Modelscited by 41
  25. 2025Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspectivecited by 34
  26. 2025Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speedcited by 33
  27. 2025Accelerating Diffusion LLM Inference via Local Determinism Propagationcited by 21
  28. 2024Unified Discrete Diffusion for Categorical Datacited by 11
  29. 2025PromptCoT 2.0: Scaling Prompt Synthesis for Large Language Model Reasoningcited by 9
  30. 2026T^star: Progressive Block Scaling for Masked Diffusion Language Models Through Trajectory Aware Reinforcement Learningcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Spec-AUF: Accept-Until-Fail Training under Train-Inference Misalignment for Masked Block Drafterscited by 3
  2. 2026Towards Unbiased On-Policy Distillation for Block Diffusion Language Modelscited by 0
  3. 2026Mask-Guided KV Cache Eviction in Block Diffusion Language Modelscited by 0
  4. 2026Enhancing Diffusion Language Models with Autoregressive Post-Training Weightscited by 0
  5. 2026Plan-and-Patch: Diffusion Language Models for Agentic Planningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Adaptive Test-Time Compute Allocation for Block Diffusion Language Models in Complex Reasoning
  2. 2026Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement Learning
  3. 2026Reasoning with Continuous Latent Diffusion
  4. 2026CAI-DLLM: Convergence Aware Inference for Diffusion Language Models
  5. 2026Escaping Confidence Trap: Evolutionary Decoding for Mathematical Reasoning in Diffusion LLMs
  6. 2026DiffCoT: Diffusion-styled Chain-of-Thought Reasoning in LLMs
  7. 2026Adaptive Block Diffusion: Resolving Training-Inference Mismatch in Diffusion Language Models
  8. 2026SemBlock: Semantic Boundary Dynamic Blocks for Diffusion LLMs