mlsanityData to 7 Oct 2026

Adaptive Test-Time Compute Allocation for Block Diffusion Language Models in Complex Reasoning

arXiv 2602.09555 ↗First posted 10 Feb 2026cs.CLcited by 2

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

also in 1 more
Abstract (arXiv)

Recent advances in block diffusion language models have demonstrated competitive performance and strong scalability on reasoning tasks. However, their test-time compute allocation remains largely unexplored, leaving a critical speed-effectiveness trade-off unresolved in long Chain-of-Thought reasoning. To address this, we propose a unified test-time compute allocation framework that introduces adaptivity in both step-wise decoding and blockwise generation. At the decoding level, we propose Bounded Adaptive Confidence Decoding (BACD), a difficulty-aware sampling strategy that dynamically adjusts denoising based on model confidence, accelerating inference while controlling error accumulation. Beyond step-wise adaptivity, we introduce the Think Coarse, Critic Fine (TCCF) paradigm that allocates large block sizes for exploratory thinking and smaller block sizes for precise refinement. To stabilize training under varying block configurations, we adopt Progressive Block Size Extension, which mitigates quality degradation when scaling up block sizes. Extensive evaluations on six benchmarks show that our TDAR-8B model with BACD and TCCF achieves a 2.38× speedup and +3.4% average accuracy over the strong TraDo-8B baseline, unlocking the potential of block diffusion in complex reasoning.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Diffusion reasoning and test-time scaling, one of 17 directions in LLM reasoning. Builds on 31 of its 36 references that are in the map. First posted on arXiv 10 Feb 2026.

Builds on

31 of 36 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Diffuse Thinking: Exploring Diffusion Language Models as Efficient Thought Proposers for Reasoning31 Oct
  2. 2024Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning18 Oct

Other references · 29

  1. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  2. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  3. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  4. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
  5. 2024OpenAI o1 System Cardcited by 1,220
  6. 2024Simple and Effective Masked Diffusion Language Modelscited by 800
  7. 2024Training Large Language Models to Reason in a Continuous Latent Spacecited by 763
  8. 2024Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMscited by 564
  9. 2025Dream 7B: Diffusion Large Language Modelscited by 515
  10. 2025Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decodingcited by 404
  11. 2025Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Modelscited by 385
  12. 2025L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learningcited by 381
17 more
  1. 2025LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Modelscited by 273
  2. 2024Scaling Diffusion Language Models via Adaptation from Autoregressive Modelscited by 268
  3. 2025Training Language Models to Reason Efficientlycited by 242
  4. 2024Scaling up Masked Diffusion Models on Textcited by 195
  5. 2025DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generationcited by 184
  6. 2025LLaDA2.0: Scaling Up Diffusion Language Models to 100Bcited by 154
  7. 2025AdaptThink: Reasoning Models Can Learn When to Thinkcited by 141
  8. 2025Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmaskingcited by 128
  9. 2025Fast-dLLM v2: Efficient Block-Diffusion LLMcited by 128
  10. 2025SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generationcited by 118
  11. 2025Thinkless: LLM Learns When to Thinkcited by 107
  12. 2025Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Modelscited by 80
  13. 2025Learn to Reason Efficiently with Adaptive Length-based Reward Shapingcited by 74
  14. 2025LLaDA-MoE: A Sparse MoE Diffusion Language Modelcited by 54
  15. 2025Wide-In, Narrow-Out: Revokable Decoding for Efficient and Effective DLLMscited by 45
  16. 2025Saber: An Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Modelcited by 13
  17. 2025DiRL: An Efficient Post-Training Framework for Diffusion Language Modelscited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Adaptive Block Diffusion: Resolving Training-Inference Mismatch in Diffusion Language Modelscited by 1
  2. 2026Escaping Confidence Trap: Evolutionary Decoding for Mathematical Reasoning in Diffusion LLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026DreamReasoner-8B: Block-Size Curriculum Learning for Diffusion Reasoning Models
  2. 2025Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning
  3. 2026Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement Learning
  4. 2026Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching
  5. 2026CAI-DLLM: Convergence Aware Inference for Diffusion Language Models
  6. 2026The Confidence Shortcut: A Reasoning Failure Mode of Masked Diffusion Models
  7. 2026Correct, Concise and Complete: Multi-stage Training For Adaptive Reasoning
  8. 2026Register Tokens for Bounded-State Reasoning in Diffusion Language Models