mlsanityData to 7 Oct 2026

DiffuTester: Accelerating Unit Test Generation for Diffusion LLMs via Mining Structural Pattern

arXiv 2509.24975 ↗First posted 29 Sep 2025cs.SE cs.CLcited by 2

Not on the map. Why?

Abstract (arXiv)

Diffusion large language models (dLLMs) enable parallel generation and are promising for unit test generation (UTG), where efficient and large-scale automated testing is essential in software development. Despite this advantage, their application to UTG is still constrained by a clear trade-off between efficiency and test quality, since increasing the number of tokens generated in each step often causes a sharp decline in the quality of test cases. To overcome this limitation, we present DiffuTester, an acceleration framework specifically tailored for dLLMs in UTG. The motivation of DiffuTester is that unit tests targeting the same focal method often share structural patterns. DiffuTester employs a novel structural pattern based decoding approach, which dynamically identifies structural patterns across unit tests through their abstract syntax trees and additionally decodes the corresponding tokens, thereby achieving acceleration without compromising the quality of the output. To enable comprehensive evaluation, we extend the original TestEval benchmark to three programming languages. Extensive experiments on three benchmarks with two representative models show that DiffuTester delivers significant acceleration while preserving test coverage. Moreover, DiffuTester generalizes well across different dLLMs and programming languages, providing a practical and scalable solution for efficient UTG in software development. Code and data are publicly available at https://github.com/THU-Agent/DiffuTester.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 35 of its 76 references that are in the map. First posted on arXiv 29 Sep 2025.

Builds on

35 of 76 references.

References · 35

  1. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,615
  2. 2023Accelerating Large Language Model Decoding with Speculative Samplingcited by 975
  3. 2025Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decodingcited by 404
  4. 2023CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-Xcited by 294
  5. 2025LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Modelscited by 273
  6. 2025Mercury: Ultra-Fast Language Models Based on Diffusioncited by 225
  7. 2025Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusionscited by 208
  8. 2024Scaling up Masked Diffusion Models on Textcited by 195
  9. 2023An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generationcited by 193
  10. 2025DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generationcited by 184
  11. 2025dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Cachingcited by 168
  12. 2023Software Testing with Large Language Models: Survey, Landscape, and Visioncited by 163
23 more
  1. 2025LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuningcited by 145
  2. 2020Unit Test Case Generation with Transformers and Focal Contextcited by 118
  3. 2025Accelerating Diffusion LLMs via Adaptive Parallel Decodingcited by 108
  4. 2025Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policiescited by 90
  5. 2025Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Evictioncited by 64
  6. 2025Diffusion Beats Autoregressive in Data-Constrained Settingscited by 61
  7. 2024Exploring and Unleashing the Power of Large Language Models in Automated Code Translationcited by 57
  8. 2025Edit Flows: Flow Matching with Edit Operationscited by 53
  9. 2023Effective Test Generation Using Pre-trained Large Language Models and Mutation Testingcited by 51
  10. 2022Pynguin: Automated Unit Test Generation for Pythoncited by 49
  11. 2024TestGenEval: A Real World Unit Test Generation and Test Completion Benchmarkcited by 49
  12. 2025LongLLaDA: Unlocking Long Context Capabilities in Diffusion LLMscited by 38
  13. 2016A Survey of Symbolic Execution Techniquescited by 36
  14. 2025Exploring the Potential of Diffusion Large Language Models in Code Generationcited by 16
  15. 2024A Large-scale Empirical Study on Fine-tuning Large Language Models for Unit Testingcited by 15
  16. 2023Unit Test Generation using Generative AI : A Comparative Performance Analysis of Autogeneration Toolscited by 13
  17. 2025Constrained Decoding of Diffusion LLMs with Context-Free Grammarscited by 13
  18. 2025TreeDiff: AST-Guided Code Generation with Diffusion LLMscited by 11
  19. 2024B4: Towards Optimal Assessment of Plausible Code Solutions with Plausible Testscited by 9
  20. 2019On the Relation Between Unit Testing and Code Qualitycited by 3
  21. 2024InterEvo-TR: Interactive Evolutionary Test Generation With Readability Assessmentcited by 3
  22. 2023Tests4Py: A Benchmark for System Testingcited by 2
  23. 2022Improve Model Testing by Integrating Bounded Model Checking and Coverage Guided Fuzzingcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025AI-Driven Self-Evolving Software: A Promising Path Toward Software Automationcited by 3
  2. 2026To See is Not to Master: Teaching LLMs to Use Private Libraries for Code Generationcited by 3