A Review of Large Language Models for Automated Test Case Generation
Problem
Manually creating test cases for software is effortful; the paper reviews whether large language models can automate test case generation.
Why it matters
Software testing consumes significant manual effort, so automation could reduce cost and speed development.
What the AI did
It is a literature review of studies using LLMs to generate test cases, comparing their effectiveness against existing tools and identifying future research directions.
Results
not stated in source
Impact
The review synthesizes opportunities and challenges of LLM-based test generation but reports no concrete measured outcome in the abstract.
Record
| Venue | Machine Learning and Knowledge Extraction |
|---|---|
| Published | 2025 |
| Work type | article |
| Authors | Arda Celik, Qusay H. Mahmoud |
| Citations | 29 (OpenAlex, at import time) |
| References | 67 |
| Model or method | not stated in source |
| Organization | not stated in source |
| Primary source | https://doi.org/10.3390/make7030097 |
| Open access | gold |
| Keywords | LLMs, test case generation, software testing, systematic review |
Importance rating
real but narrower advance
Software testing is effortful and automation could reduce cost, but this is a literature review with no concrete measured outcomes reported in the abstract.
More in Software & Coding
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | ImageNet classification with deep convolutional neural networks | 2017 | 106,345 |
8
|
| 2 | Deep Residual Learning for Image Recognition | 2016 | 221,134 |
8
|
| 3 | Faster sorting algorithms discovered using deep reinforcement learning | 2023 | 175 |
8
|
| 4 | A deep learning‐based approach for software vulnerability detection using code metrics | 2022 | 42 |
7
|
| 5 | Deep Learning-Based Attack Detection and Classification in Android Devices | 2023 | 41 |
7
|