# On the Reasoning Abilities of Masked Diffusion Language Models

arXiv: https://arxiv.org/abs/2510.13117 · HTML: https://mlsanity.com/paper/2510.13117/

## Key facts

- Cited by 7 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 30 of its 63 references that are in the map.
- First posted on arXiv 15 Oct 2025.

## Placed in

- LLM reasoning / [Diffusion reasoning and test-time scaling](https://mlsanity.com/lr/diffusion-reasoning-and-test-time-scaling/)
- Diffusion models / [Discrete and text diffusion](https://mlsanity.com/diffusion/discrete-and-text-diffusion/)

## Builds on (most cited first, 30 of 30)

- [Large Language Diffusion Models](https://mlsanity.com/paper/2502.09992/) (2025)
- [Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution](https://mlsanity.com/paper/2310.16834/) (2023)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [Universal Transformers](https://mlsanity.com/paper/1807.03819/) (2018)
- [Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding](https://mlsanity.com/paper/2505.22618/) (2025)
- [Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models](https://mlsanity.com/paper/2503.09573/) (2025)
- [Reasoning with Latent Thoughts: On the Power of Looped Transformers](https://mlsanity.com/paper/2502.17416/) (2025)
- [Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions](https://mlsanity.com/paper/2502.06768/) (2025)
- [DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation](https://mlsanity.com/paper/2506.20639/) (2025)
- [Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference](https://mlsanity.com/paper/2508.02193/) (2025)
- [A Reparameterized Discrete Diffusion Model for Text Generation](https://mlsanity.com/paper/2302.05737/) (2023)
- [Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning](https://mlsanity.com/paper/2410.14157/) (2024)
- [Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation](https://mlsanity.com/paper/2507.10524/) (2025)
- [Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmasking](https://mlsanity.com/paper/2505.24857/) (2025)
- [Path Planning for Masked Diffusion Model Sampling](https://mlsanity.com/paper/2502.03540/) (2025)
- [Think While You Generate: Discrete Diffusion with Planned Denoising](https://mlsanity.com/paper/2410.06264/) (2024)
- [A Little Depth Goes a Long Way: The Expressive Power of Log-Depth Transformers](https://mlsanity.com/paper/2503.03961/) (2025)
- [Theoretical Benefit and Limitation of Diffusion Language Model](https://mlsanity.com/paper/2502.09622/) (2025)
- [Convergence Analysis of Discrete Diffusion Model: Exact Implementation through Uniformization](https://mlsanity.com/paper/2402.08095/) (2024)
- [A Survey on Parallel Text Generation: From Parallel Decoding to Diffusion Language Models](https://mlsanity.com/paper/2508.08712/) (2025)
- [Breaking AR's Sampling Bottleneck: Provable Acceleration via Diffusion Language Models](https://mlsanity.com/paper/2505.21400/) (2025)
- [Exact Expressive Power of Transformers with Padding](https://mlsanity.com/paper/2505.18948/) (2025)
- [Speed Always Wins: A Survey on Efficient Architectures for Large Language Models](https://mlsanity.com/paper/2508.09834/) (2025)
- [Characterizing the Expressivity of Fixed-Precision Transformer Language Models](https://mlsanity.com/paper/2505.23623/) (2025)
- [The Serial Scaling Hypothesis](https://mlsanity.com/paper/2507.12549/) (2025)
- [To CoT or To Loop? A Formal Comparison Between Chain-of-Thought and Looped Transformers](https://mlsanity.com/paper/2505.19245/) (2025)
- [Unique Hard Attention: A Tale of Two Sides](https://mlsanity.com/paper/2503.14615/) (2025)
- [Pause Tokens Strictly Increase the Expressivity of Constant-Depth Transformers](https://mlsanity.com/paper/2505.21024/) (2025)
- [Formal Aspects of Language Modeling](https://mlsanity.com/paper/2311.04329/) (2023)
- [Perfect diffusion is mathsfTC0 -- Bad diffusion is Turing-complete](https://mlsanity.com/paper/2507.12469/) (2025)

## Built on by (most cited first, 7 of 7)

- [Where-to-Unmask: Ground-Truth-Guided Unmasking Order Learning for Masked Diffusion Language Models](https://mlsanity.com/paper/2602.09501/) (2026)
- [Recursive Scaling in Masked Diffusion Models](https://mlsanity.com/paper/2606.18022/) (2026)
- [GeoBlock: Inferring Block Granularity from Dependency Geometry in Diffusion Language Models](https://mlsanity.com/paper/2603.26675/) (2026)
- [Looped Diffusion Language Models](https://mlsanity.com/paper/2605.26106/) (2026)
- [Revisiting Padded Transformer Expressivity: Which Architectural Choices Matter and Which Don't](https://mlsanity.com/paper/2605.30523/) (2026)
- [Towards Efficient Reasoning: Learning Causal Shortcuts for Diffusion Language Models](https://mlsanity.com/paper/2609.28272/) (2026)
- [RL Post-Training Diffusion Language Models Along Their Own Generation Paths](https://mlsanity.com/paper/2610.17266/) (2026)

## Abstract (arXiv)

Masked diffusion models (MDMs) for text offer a compelling alternative to traditional autoregressive language models. Parallel generation makes them efficient, but their computational capabilities and the limitations inherent in their parallelism remain largely unexplored. To this end, we characterize what types of reasoning problems MDMs can provably solve and how efficiently. We do this by connecting MDMs to the well-understood reasoning frameworks of chain of thought (CoT) and padded looped transformers (PLTs) in the finite-precision log-width setting: We show that MDMs and polynomially-padded PLTs are, in fact, equivalent in this setting, and that MDMs can solve all problems that CoT-augmented transformers can. Moreover, we showcase classes of problems (including regular languages) for which MDMs are inherently more efficient than CoT transformers, where parallel generation allows for substantially faster reasoning.