Next-Generation Software Testing with Generative AI: LLMs, Self-Healing Systems, and Implementation Insights.
Saved in:
| Title: | Next-Generation Software Testing with Generative AI: LLMs, Self-Healing Systems, and Implementation Insights. |
|---|---|
| Authors: | Pacholi, Nisha1, Bahad, Pritika2, Chauhan, Dipti2 diptichauhan09@gmail.com |
| Source: | Journal of Engineering Science & Technology Review. 2025, Vol. 18 Issue 6, p200-208. 9p. |
| Subjects: | Generative artificial intelligence, Computer software testing, Dynamic testing, Language models, Test systems |
| Abstract: | Generative Artificial Intelligence has become a disruptive emblem of software testing, providing the capability of greater automation, flexibility, and intelligent testing life cycle. The recent developments in large-scale models, multimodal transformers and reinforcement learning experiences have reshaped the concept of test case generation, defect prediction and test data synthesis. Compared to conventional automation, which considers only rules, the GenAI systems are able to dynamically adjust to changing codebases, are able to speed up CI/CD processes, and are able to create more resilience by having self-healing testing infrastructure. The paper reinvents the classical techniques and incorporates the most recent advances in the test design with the use of LLM, explainable anomaly detection, and Edge AI as the method of decentralized validation. According to experimental implementation results, it has shown considerable improvements with an 92 percent coverage rate on tests with and an 85 percent accuracy on detection on defects and more than 50 percent of time savings on regression tests as compared to the traditional methods. The examples of finance, healthcare, and automotive industries show the transformative power of GenAI, whereas the issues of explainability, data quality, and computational sustainability are still acute. We conclude by highlighting emerging trends in hybrid human-AI testing teams and the future trajectory of autonomous testing agents. [ABSTRACT FROM AUTHOR] |
| Copyright of Journal of Engineering Science & Technology Review is the property of Technological Education Institute of Kavala and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Links: – Type: pdflink Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 191030943 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Next-Generation Software Testing with Generative AI: LLMs, Self-Healing Systems, and Implementation Insights. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Pacholi%2C+Nisha%22">Pacholi, Nisha</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Bahad%2C+Pritika%22">Bahad, Pritika</searchLink><relatesTo>2</relatesTo><br /><searchLink fieldCode="AR" term="%22Chauhan%2C+Dipti%22">Chauhan, Dipti</searchLink><relatesTo>2</relatesTo><i> diptichauhan09@gmail.com</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Journal+of+Engineering+Science+%26+Technology+Review%22">Journal of Engineering Science & Technology Review</searchLink>. 2025, Vol. 18 Issue 6, p200-208. 9p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Generative+artificial+intelligence%22">Generative artificial intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+software+testing%22">Computer software testing</searchLink><br /><searchLink fieldCode="DE" term="%22Dynamic+testing%22">Dynamic testing</searchLink><br /><searchLink fieldCode="DE" term="%22Language+models%22">Language models</searchLink><br /><searchLink fieldCode="DE" term="%22Test+systems%22">Test systems</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Generative Artificial Intelligence has become a disruptive emblem of software testing, providing the capability of greater automation, flexibility, and intelligent testing life cycle. The recent developments in large-scale models, multimodal transformers and reinforcement learning experiences have reshaped the concept of test case generation, defect prediction and test data synthesis. Compared to conventional automation, which considers only rules, the GenAI systems are able to dynamically adjust to changing codebases, are able to speed up CI/CD processes, and are able to create more resilience by having self-healing testing infrastructure. The paper reinvents the classical techniques and incorporates the most recent advances in the test design with the use of LLM, explainable anomaly detection, and Edge AI as the method of decentralized validation. According to experimental implementation results, it has shown considerable improvements with an 92 percent coverage rate on tests with and an 85 percent accuracy on detection on defects and more than 50 percent of time savings on regression tests as compared to the traditional methods. The examples of finance, healthcare, and automotive industries show the transformative power of GenAI, whereas the issues of explainability, data quality, and computational sustainability are still acute. We conclude by highlighting emerging trends in hybrid human-AI testing teams and the future trajectory of autonomous testing agents. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Journal of Engineering Science & Technology Review is the property of Technological Education Institute of Kavala and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=191030943 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.25103/jestr.186.21 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 9 StartPage: 200 Subjects: – SubjectFull: Generative artificial intelligence Type: general – SubjectFull: Computer software testing Type: general – SubjectFull: Dynamic testing Type: general – SubjectFull: Language models Type: general – SubjectFull: Test systems Type: general Titles: – TitleFull: Next-Generation Software Testing with Generative AI: LLMs, Self-Healing Systems, and Implementation Insights. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Pacholi, Nisha – PersonEntity: Name: NameFull: Bahad, Pritika – PersonEntity: Name: NameFull: Chauhan, Dipti IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 11 Text: 2025 Type: published Y: 2025 Identifiers: – Type: issn-print Value: 17912377 Numbering: – Type: volume Value: 18 – Type: issue Value: 6 Titles: – TitleFull: Journal of Engineering Science & Technology Review Type: main |
| ResultId | 1 |
