Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement Learning

• URL: http://arxiv.org/abs/2605.02263v1
• Date: Mon, 04 May 2026 06:17:49 GMT
• Title: Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement Learning
• Abstract summary: The fixed-size block generations remain a critical bottleneck for effective and coherent reasoning.<n>This paper proposes b1, a novel post-training framework for dLLMs that learns dynamic-size reasoning blocks via a Monotonic Entropy Descent objective.
• Score: 41.859993506122194
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent diffusion large language models (dLLMs) have demonstrated both effectiveness and efficiency in reasoning via a block-based semi-autoregressive generation paradigm. Despite their progress, the fixed-size block generations remain a critical bottleneck for effective and coherent reasoning. 1. From a global perspective, different reasoning tasks would correspond to different optimal decoding block sizes, which makes a ``one-size-fits-all'' assumption ineffective. 2. Even within a single reasoning task, the rigid block partitioning would break the logical flow and reduce reasoning coherence. Through empirical observations, we reveal that for block-wise entropy, incorrect reasoning exhibits a fluctuating and unsteady trend between blocks, whereas the correctly generated tasks follow a consistent descending trend. Therefore, this paper proposes b1, a novel post-training framework for dLLMs that learns dynamic-size reasoning blocks via a Monotonic Entropy Descent objective with reinforcement learning to enhance reasoning coherence.b1 integrates seamlessly as a plug-and-play module with existing dLLM's post-training algorithms. Extensive experiments across various reasoning benchmarks showcase b1's consistent improvement over existing fixed-size block baselines. Our code has been released at https://github.com/YanJiangJerry/Block-R1.

Related papers

• DreamReasoner-8B: Block-Size Curriculum Learning for Diffusion Reasoning Models [82.86749180125919]
  We develop DreamReasoner-8B, an open-source block diffusion reasoning model.<n>Our analysis reveals a stark performance disparity: training with large block sizes yields remarkably poor reasoning.<n>We propose block-size curriculum learning, which gradually transitions training from fine-grained to coarse-grained block sizes.
  arXiv  Detail & Related papers  (2026-06-17T16:34:02Z)
• BlockBatch: Multi-Scale Consensus Decoding for Efficient Diffusion Language Model Inference [15.424211656458453]
  Diffusion language models generate text by iteratively denoising multiple token positions in parallel.<n>Small blocks preserve local conditioning but require many denoising steps, whereas large blocks expose more parallelism but can make premature commitments and accumulate cache error.<n>We propose BlockBatch, a training-free online inference framework that executes multiple block-size branches for the same request inside a batched forward pass.
  arXiv  Detail & Related papers  (2026-05-28T01:48:29Z)
• Advancing Block Diffusion Language Models for Test-Time Scaling [73.54022593833638]
  We propose a unified framework for test-time scaling in BDLMs.<n>We introduce adaptivity in both decoding and block-wise generation.<n>We show that applying BACD and TCCF to TDAR-8B yields significant improvements over strong baselines.
  arXiv  Detail & Related papers  (2026-02-10T09:05:07Z)
• DSB: Dynamic Sliding Block Scheduling for Diffusion LLMs [17.284485483927448]
  Diffusion large language models (dLLMs) have emerged as a promising alternative for text generation.<n>The widely-used fixed, predefined block (naive) schedule is agnostic to semantic difficulty, making it a suboptimal strategy for both quality and efficiency.<n>We propose Dynamic Sliding Block (DSB), a training-free block scheduling method that uses a sliding block with a dynamic size to overcome the rigidity of the naive block.
  arXiv  Detail & Related papers  (2026-02-05T18:41:38Z)
• From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs [58.640039233470766]
  We show that principled AR-to-block-diffusion adaptation is an effective and compute-efficient alternative to training DLMs from scratch.<n> NBDiff-7B (Base and Instruct) could inherit the long-context modeling and reasoning capabilities, and achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-12-07T10:28:21Z)
• Blockwise SFT for Diffusion Language Models: Reconciling Bidirectional Attention and Autoregressive Decoding [60.06816407728172]
  Discrete diffusion language models have shown strong potential for text generation.<n>Standard supervised fine-tuning misaligns with semi-autoregressive inference.<n>We propose Blockwise SFT, which partitions responses into fixed-size blocks.
  arXiv  Detail & Related papers  (2025-08-27T02:49:33Z)
• Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning [3.773711855945839]
  Large Language Models (LLMs) with chains-of-thought have demonstrated strong performance on an increasing range of tasks.<n>This raises a question: can LLMs dynamically adjust the length of their reasoning processes based on task complexity?<n>We propose the Think in Blocks framework, which enables adaptive reasoning-from zero to deep reasoning-by partitioning the reasoning process into a tunable number of blocks.
  arXiv  Detail & Related papers  (2025-08-21T12:32:19Z)
• Towards Universal Dense Blocking for Entity Resolution [49.06313308481536]
  We propose UniBlocker, a dense blocker that is pre-trained on a domain-independent, easily-obtainable corpus. By conducting domain-independent pre-training, UniBlocker can be adapted to various downstream blocking scenarios without requiring domain-specific fine-tuning. Our experiments show that the proposed UniBlocker, without any domain-specific learning, significantly outperforms previous self- and unsupervised dense blocking methods.
  arXiv  Detail & Related papers  (2024-04-23T08:39:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.