Academic Journal
Προβολή σε EDS

GPT‐Monkey: Enhancing Automated GUI Testing for Android Apps via LLM‐Driven Interface Understanding and Function Segmentation.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: GPT‐Monkey: Enhancing Automated GUI Testing for Android Apps via LLM‐Driven Interface Understanding and Function Segmentation.
Συγγραφείς: Yuan, Zhanhui1 (AUTHOR), Chen, Kai2 (AUTHOR) chenkai@iie.ac.cn, Yang, Zhi1 (AUTHOR), Jiang, Dongxue3 (AUTHOR), Tan, Jinglei1 (AUTHOR), Zhang, Hongqi1 (AUTHOR), Marchetto, Alessandro (AUTHOR) alessandro.marchetto@unitn.it
Πηγή: IET Software (Wiley-Blackwell). 6/4/2026, Vol. 2026, p1-29. 29p.
Θεματικοί όροι: *Defect tracking (Computer software development), *Computer software quality control, Computer software testing, Parameterization, Language models, Mobile apps
Reviews & Products: Android (Operating system)
Περίληψη: Automated graphical user interface (GUI) testing is essential for ensuring mobile app quality. However, existing related methods lack deep GUI understanding and cannot segment specific functions for targeted testing, resulting in wasted test events and low efficiency. This study aims to leverage large language models (LLMs) to enhance Monkey‐based GUI testing by enabling function‐level segmentation and tailored parameter generation driven by user requirements. We propose GPT‐Monkey, which integrates Monkey's randomness with LLM's understanding capability. It establishes global interface associations and cross‐modal alignment for LLM‐driven function segmentation, employs parameter‐retrieval augmented generation (RAG) to guide tailored parameter generation, and adopts a dual‐feedback mechanism to iteratively optimize testing. Experiments show that GPT‐Monkey improves crash detection by 16.7% and efficiency by 34.5% over the optimal baseline, and achieves 95% function segmentation accuracy and uncovers 397 real‐world crashes on 1000 Google Play apps. The results demonstrate that LLM‐driven function segmentation and tailored parameter generation significantly enhance the precision and efficiency of automated GUI testing. [ABSTRACT FROM AUTHOR]
Copyright of IET Software (Wiley-Blackwell) is the property of Wiley-Blackwell 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.)
Βάση Δεδομένων: Business Source Index
FullText Links:
  – Type: other
Text:
  Availability: 0
Header DbId: bsx
DbLabel: Business Source Index
An: 194296404
RelevancyScore: 1435
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1435
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: GPT‐Monkey: Enhancing Automated GUI Testing for Android Apps via LLM‐Driven Interface Understanding and Function Segmentation.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Yuan%2C+Zhanhui%22">Yuan, Zhanhui</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Chen%2C+Kai%22">Chen, Kai</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> chenkai@iie.ac.cn</i><br /><searchLink fieldCode="AR" term="%22Yang%2C+Zhi%22">Yang, Zhi</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Jiang%2C+Dongxue%22">Jiang, Dongxue</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Tan%2C+Jinglei%22">Tan, Jinglei</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhang%2C+Hongqi%22">Zhang, Hongqi</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Marchetto%2C+Alessandro%22">Marchetto, Alessandro</searchLink> (AUTHOR)<i> alessandro.marchetto@unitn.it</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22IET+Software+%28Wiley-Blackwell%29%22">IET Software (Wiley-Blackwell)</searchLink>. 6/4/2026, Vol. 2026, p1-29. 29p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Defect+tracking+%28Computer+software+development%29%22">Defect tracking (Computer software development)</searchLink><br />*<searchLink fieldCode="DE" term="%22Computer+software+quality+control%22">Computer software quality control</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+software+testing%22">Computer software testing</searchLink><br /><searchLink fieldCode="DE" term="%22Parameterization%22">Parameterization</searchLink><br /><searchLink fieldCode="DE" term="%22Language+models%22">Language models</searchLink><br /><searchLink fieldCode="DE" term="%22Mobile+apps%22">Mobile apps</searchLink>
– Name: SubjectProduct
  Label: Reviews & Products
  Group: Su
  Data: <searchLink fieldCode="PS" term="%22Android+%28Operating+system%29%22">Android (Operating system)</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Automated graphical user interface (GUI) testing is essential for ensuring mobile app quality. However, existing related methods lack deep GUI understanding and cannot segment specific functions for targeted testing, resulting in wasted test events and low efficiency. This study aims to leverage large language models (LLMs) to enhance Monkey‐based GUI testing by enabling function‐level segmentation and tailored parameter generation driven by user requirements. We propose GPT‐Monkey, which integrates Monkey's randomness with LLM's understanding capability. It establishes global interface associations and cross‐modal alignment for LLM‐driven function segmentation, employs parameter‐retrieval augmented generation (RAG) to guide tailored parameter generation, and adopts a dual‐feedback mechanism to iteratively optimize testing. Experiments show that GPT‐Monkey improves crash detection by 16.7% and efficiency by 34.5% over the optimal baseline, and achieves 95% function segmentation accuracy and uncovers 397 real‐world crashes on 1000 Google Play apps. The results demonstrate that LLM‐driven function segmentation and tailored parameter generation significantly enhance the precision and efficiency of automated GUI testing. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of IET Software (Wiley-Blackwell) is the property of Wiley-Blackwell 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=bsx&AN=194296404
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1049/sfw2/9976714
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 29
        StartPage: 1
    Subjects:
      – SubjectFull: Defect tracking (Computer software development)
        Type: general
      – SubjectFull: Computer software quality control
        Type: general
      – SubjectFull: Computer software testing
        Type: general
      – SubjectFull: Parameterization
        Type: general
      – SubjectFull: Language models
        Type: general
      – SubjectFull: Mobile apps
        Type: general
      – SubjectFull: Android (Operating system)
        Type: general
    Titles:
      – TitleFull: GPT‐Monkey: Enhancing Automated GUI Testing for Android Apps via LLM‐Driven Interface Understanding and Function Segmentation.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Yuan, Zhanhui
      – PersonEntity:
          Name:
            NameFull: Chen, Kai
      – PersonEntity:
          Name:
            NameFull: Yang, Zhi
      – PersonEntity:
          Name:
            NameFull: Jiang, Dongxue
      – PersonEntity:
          Name:
            NameFull: Tan, Jinglei
      – PersonEntity:
          Name:
            NameFull: Zhang, Hongqi
      – PersonEntity:
          Name:
            NameFull: Marchetto, Alessandro
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 04
              M: 06
              Text: 6/4/2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 17518806
          Numbering:
            – Type: volume
              Value: 2026
          Titles:
            – TitleFull: IET Software (Wiley-Blackwell)
              Type: main
ResultId 1