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

arXiv:2509.24975 · cs.SE, cs.CL · Submitted 2025-09-29 · Read on arXiv

cs.SE, cs.CL

Submitted: 2025-09-29

Updated: 2026-09-12

Comments: Update format and add some experimental results

Code: https://github.com/THU-Agent/DiffuTester

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 26× in this paper · explained in 2 episodes
• Decode — 7× in this paper · explained in 2 episodes
• Diffusion Model — 6× in this paper · explained in 8 episodes
• Diffusion Models — 6× in this paper · explained in 6 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Ablation study — 3× in this paper · explained in 1 episode
• Core — 3× in this paper · explained in 2 episodes
• Benchmarking — 2× in this paper · explained in 3 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• GRPO — 2× in this paper · explained in 6 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Computational overhead — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Fingerprinting — 1× in this paper · explained in 2 episodes
• Flow Matching — 1× in this paper · explained in 7 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Human-in-the-Loop — 1× in this paper · explained in 3 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• Speculative Decoding — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Accelerating Large Language Model Decoding with Speculative Sampling
• SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation
• GPT-4 Technical Report
• Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmasking
• Investigating Data Contamination in Modern Benchmarks for Large Language Models
• Fast Inference from Transformers via Speculative Decoding
• DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation
• Exploring the Potential of Diffusion Large Language Models in Code Generation
• Beyond Fixed: Training-Free Variable-Length Denoising for Diffusion Large Language Models
• A Survey on Diffusion Language Models
• Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies
• Qwen2.5-Coder Technical Report
• LongLLaDA: Unlocking Long Context Capabilities in Diffusion LLMs
• Accelerating Diffusion LLMs via Adaptive Parallel Decoding
• TestGenEval: A Real World Unit Test Generation and Test Completion Benchmark
• Mercury: Ultra-Fast Language Models Based on Diffusion
• Constrained Decoding of Diffusion LLMs with Context-Free Grammars
• Scaling up Masked Diffusion Models on Text
• Large Language Diffusion Models
• Unit Test Case Generation with Transformers and Focal Context

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties