View in EDS PDF Full Text

Large Language Model Selection for Test-Driven Prompt Android iOS Development.

Saved in:
Bibliographic Details
Title: Large Language Model Selection for Test-Driven Prompt Android iOS Development.
Authors: Rizqullah, Muhammad1 mrizqullah@stu.kau.edu.sa, Albassam, Emad1
Source: International Journal of Interactive Mobile Technologies. 2026, Vol. 20 Issue 3, p71-82. 12p.
Subjects: Mobile app development, iOS (Operating system), Empirical research, Code generators, Android (Operating system), Prompt engineering, Language models
Abstract: Large language model (LLM) code generation research predominantly focuses on Python, with test-driven prompt engineering exclusively targeting this language. This study presents a comprehensive LLM selection framework for mobile development through rigorous empirical analysis. We conducted 8,704 evaluations across 544 programming tasks (HumanEval and MBPP datasets) on Android (Java) and iOS (Swift) platforms using four state-of-the-art LLMs (GPT-4o, GPT-4o-mini, Qwen 14B, and Qwen 32B), two prompting strategies (base and test-driven), and two metrics (accuracy and remediation accuracy). Systematic analysis of platform-specific patterns yielded a decision tree incorporating first-attempt correctness, budget constraints, and self-hosting requirements, validated through three industry-relevant use cases. Results show test-driven prompting (TDP) achieves a +2.22 pp average accuracy improvement over baseline (95% CI [1.22-3.23 pp], p < 0.001, d = 0.3974). However, LLMs consistently underperform in mobile development (66.85%--88.87%) compared to Pythonbased code generation (86.90%-91.30%) regardless of model size or type. This framework establishes groundwork for platform-specific optimizations while providing practitioners with actionable guidance for model selection in mobile development contexts. [ABSTRACT FROM AUTHOR]
Copyright of International Journal of Interactive Mobile Technologies is the property of International Journal of Interactive Mobile Technologies 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: 191627704
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Large Language Model Selection for Test-Driven Prompt Android iOS Development.
– Name: Author
  Label: Authors
  Group: Au
  Data: &lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Rizqullah%2C+Muhammad%22&quot;&gt;Rizqullah, Muhammad&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt;&lt;i&gt; mrizqullah@stu.kau.edu.sa&lt;/i&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Albassam%2C+Emad%22&quot;&gt;Albassam, Emad&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt;
– Name: TitleSource
  Label: Source
  Group: Src
  Data: &lt;searchLink fieldCode=&quot;JN&quot; term=&quot;%22International+Journal+of+Interactive+Mobile+Technologies%22&quot;&gt;International Journal of Interactive Mobile Technologies&lt;/searchLink&gt;. 2026, Vol. 20 Issue 3, p71-82. 12p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: &lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Mobile+app+development%22&quot;&gt;Mobile app development&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22iOS+%28Operating+system%29%22&quot;&gt;iOS (Operating system)&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Empirical+research%22&quot;&gt;Empirical research&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Code+generators%22&quot;&gt;Code generators&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Android+%28Operating+system%29%22&quot;&gt;Android (Operating system)&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Prompt+engineering%22&quot;&gt;Prompt engineering&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Language+models%22&quot;&gt;Language models&lt;/searchLink&gt;
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Large language model (LLM) code generation research predominantly focuses on Python, with test-driven prompt engineering exclusively targeting this language. This study presents a comprehensive LLM selection framework for mobile development through rigorous empirical analysis. We conducted 8,704 evaluations across 544 programming tasks (HumanEval and MBPP datasets) on Android (Java) and iOS (Swift) platforms using four state-of-the-art LLMs (GPT-4o, GPT-4o-mini, Qwen 14B, and Qwen 32B), two prompting strategies (base and test-driven), and two metrics (accuracy and remediation accuracy). Systematic analysis of platform-specific patterns yielded a decision tree incorporating first-attempt correctness, budget constraints, and self-hosting requirements, validated through three industry-relevant use cases. Results show test-driven prompting (TDP) achieves a +2.22 pp average accuracy improvement over baseline (95% CI [1.22-3.23 pp], p &lt; 0.001, d = 0.3974). However, LLMs consistently underperform in mobile development (66.85%--88.87%) compared to Pythonbased code generation (86.90%-91.30%) regardless of model size or type. This framework establishes groundwork for platform-specific optimizations while providing practitioners with actionable guidance for model selection in mobile development contexts. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: &lt;i&gt;Copyright of International Journal of Interactive Mobile Technologies is the property of International Journal of Interactive Mobile Technologies and its content may not be copied or emailed to multiple sites without the copyright holder&#39;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.&lt;/i&gt; (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=191627704
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3991/ijim.v20i03.59861
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 12
        StartPage: 71
    Subjects:
      – SubjectFull: Mobile app development
        Type: general
      – SubjectFull: iOS (Operating system)
        Type: general
      – SubjectFull: Empirical research
        Type: general
      – SubjectFull: Code generators
        Type: general
      – SubjectFull: Android (Operating system)
        Type: general
      – SubjectFull: Prompt engineering
        Type: general
      – SubjectFull: Language models
        Type: general
    Titles:
      – TitleFull: Large Language Model Selection for Test-Driven Prompt Android iOS Development.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Rizqullah, Muhammad
      – PersonEntity:
          Name:
            NameFull: Albassam, Emad
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 02
              Text: 2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 18657923
          Numbering:
            – Type: volume
              Value: 20
            – Type: issue
              Value: 3
          Titles:
            – TitleFull: International Journal of Interactive Mobile Technologies
              Type: main
ResultId 1