The integration of machine learning into automated test generation: A systematic mapping study
importance 5/10
partially solved
Software Testing and Debugging Techniques software testing stage: research
Problem
Automated generation of software tests is difficult; machine learning may make it effective, but the field's state was unclear.
Why it matters
Better automated testing could reduce software bugs and the cost of quality assurance.
What the AI did
This is a systematic mapping study of 124 publications characterizing how ML is used to generate test inputs, oracles, and improve existing methods.
Results
not stated in source
Impact
The survey finds ML-based test generation shows great promise but no concrete benchmark result is stated.
Record
| Venue | Software Testing Verification and Reliability |
|---|---|
| Published | 2023 |
| Work type | article |
| Authors | Afonso Fontes, Gregory Gay |
| Citations | 24 (OpenAlex, at import time) |
| References | 141 |
| Model or method | not stated in source |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1002/stvr.1845 |
| Open access | hybrid |
| Keywords | machine learning, automated test generation, systematic mapping, software testing, oracles |
Importance rating
5
real but narrower advance
Automated test generation could reduce software bugs and QA cost across the industry, but abstract gives no scale; a mapping study of 124 publications showing promise with open challenges.
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
|