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

Description
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]
ISSN:	18657923
DOI:	10.3991/ijim.v20i03.59861