mlsanityData to 7 Oct 2026

Improving Diffusion Language Model Decoding through Joint Search in Generation Order and Token Space

arXiv 2601.20339 ↗First posted 28 Jan 2026cs.CL cs.LGcited by 10

On the map: Diffusion models → Discrete and text diffusion

Abstract (arXiv)

Diffusion Language Models (DLMs) offer order-agnostic generation that can explore many possible decoding trajectories. However, current decoding methods commit to a single trajectory, limiting exploration in trajectory space. We introduce Order-Token Search to explore this space through jointly searching over generation order and token values. Its core is a likelihood estimator that scores denoising actions, enabling stable pruning and efficient exploration of diverse trajectories. Across mathematical reasoning and coding benchmarks, Order-Token Search consistently outperforms baselines on GSM8K, MATH500, Countdown, and HumanEval (3.1%, 3.8%, 7.9%, and 6.8% absolute over backbone), matching or surpassing diffu-GRPO post-trained d1-LLaDA. Our work establishes joint search as a key component for advancing decoding in DLMs.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Placed in Discrete and text diffusion, one of 14 directions in Diffusion models. Builds on 27 of its 28 references that are in the map. First posted on arXiv 28 Jan 2026.

Builds on

27 of 28 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models12 Mar
  2. 2025Remasking Discrete Diffusion Models with Inference-Time Scaling1 Mar
  3. 2025Large Language Diffusion Models14 Feb
  4. 2025Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions10 Feb
  5. 2024Scaling up Masked Diffusion Models on Text24 Oct
  6. 2024Simple and Effective Masked Diffusion Language Models11 Jun
  7. 2024Simplified and Generalized Masked Diffusion for Discrete Data6 Jun
  8. 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution25 Oct
  9. 2023Likelihood-Based Diffusion Language Models30 May

Other references · 18

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  7. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  8. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  9. 2023Let's Verify Step by Stepcited by 3,598
  10. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
  11. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,615
  12. 2025Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?cited by 948
6 more
  1. 2025LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Modelscited by 273
  2. 2025A General Framework for Inference-time Scaling and Steering of Diffusion Modelscited by 201
  3. 2025d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learningcited by 178
  4. 2022Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generationcited by 169
  5. 2022Let Invariant Rationale Discovery Inspire Graph Contrastive Learningcited by 57
  6. 2025Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcingcited by 37

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 10.

10 papers.

  1. 2026Locally Confident, Globally Stuck: The Quality-Exploration Dilemma in Diffusion Language Modelscited by 5
  2. 2026A Tale of Two Temperatures: Simple, Efficient, and Diverse Sampling from Diffusion Language Modelscited by 5
  3. 2026Search or Accelerate: Confidence-Switched Position Beam Search for Diffusion Language Modelscited by 3
  4. 2026Neither Parallel Nor Sequential: How DiffusionGemma Actually Commits Tokenscited by 2
  5. 2026Decoding in Order-Agnostic Language Models: Chain-Rule Deviation and Uniform Spreadingcited by 0
  6. 2026From Interface to Inference: Eliciting Any-Order Inference from Any-Order Modelscited by 0
  7. 2026Escaping Confidence Trap: Evolutionary Decoding for Mathematical Reasoning in Diffusion LLMscited by 0
  8. 2026Unmask the State: When Does State Adaptation Matter for Masked Diffusion Language Modelscited by 0
  9. 2026Blackboard Intelligence Can Surpass Autoregressive on Globally Constrained Problemscited by 0
  10. 2026Fork-dLLM: Avoiding the Flexibility Trap in Diffusion Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025From Bits to Rounds: Parallel Decoding with Exploration for Diffusion Language Models
  2. 2026Who Should Lead Decoding Now? Tracking Reliable Trajectories for Ensembling Masked Diffusion Language Models
  3. 2026Trajectory-Level Speculative Decoding for Diffusion Language Models
  4. 2025Beyond Confidence: Adaptive and Coherent Decoding for Diffusion Language Models
  5. 2025Diffusion Language Model Inference with Monte Carlo Tree Search
  6. 2025Diffusion Language Models Know the Answer Before Decoding
  7. 2025Decoding Large Language Diffusion Models with Foreseeing Movement
  8. 2026Roll Out and Roll Back: Diffusion LLMs are Their Own Efficiency Teachers