Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.20896 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915265895202816 |
|---|---|
| author | Fatin, Shamit Al-Quvi, Mehbubul Hasan Shahgir, Haz Sameen Barua, Sukarna Iqbal, Anindya Sharmin, Sadia Akbar, Md. Mostofa Pal, Kallol Kumar Rashid, A. Asif Al |
| author_facet | Fatin, Shamit Al-Quvi, Mehbubul Hasan Shahgir, Haz Sameen Barua, Sukarna Iqbal, Anindya Sharmin, Sadia Akbar, Md. Mostofa Pal, Kallol Kumar Rashid, A. Asif Al |
| contents | Given natural language test case description for an Android application, existing testing approaches require developers to manually write scripts using tools such as Appium and Espresso to execute the corresponding test case. This process is labor-intensive and demands significant effort to maintain as UI interfaces evolve throughout development. In this work, we introduce LELANTE, a novel framework that utilizes large language models (LLMs) to automate test case execution without requiring pre-written scripts. LELANTE interprets natural language test case descriptions, iteratively generate action plans, and perform the actions directly on the Android screen using its GUI. LELANTE employs a screen refinement process to enhance LLM interpretability, constructs a structured prompt for LLMs, and implements an action generation mechanism based on chain-of-thought reasoning of LLMs. To further reduce computational cost and enhance scalability, LELANTE utilizes model distillation using a foundational LLM. In experiments across 390 test cases spanning 10 popular Android applications, LELANTE achieved a 73% test execution success rate. Our results demonstrate that LLMs can effectively bridge the gap between natural language test case description and automated execution, making mobile testing more scalable and adaptable. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_20896 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LELANTE: LEveraging LLM for Automated ANdroid TEsting Fatin, Shamit Al-Quvi, Mehbubul Hasan Shahgir, Haz Sameen Barua, Sukarna Iqbal, Anindya Sharmin, Sadia Akbar, Md. Mostofa Pal, Kallol Kumar Rashid, A. Asif Al Software Engineering Given natural language test case description for an Android application, existing testing approaches require developers to manually write scripts using tools such as Appium and Espresso to execute the corresponding test case. This process is labor-intensive and demands significant effort to maintain as UI interfaces evolve throughout development. In this work, we introduce LELANTE, a novel framework that utilizes large language models (LLMs) to automate test case execution without requiring pre-written scripts. LELANTE interprets natural language test case descriptions, iteratively generate action plans, and perform the actions directly on the Android screen using its GUI. LELANTE employs a screen refinement process to enhance LLM interpretability, constructs a structured prompt for LLMs, and implements an action generation mechanism based on chain-of-thought reasoning of LLMs. To further reduce computational cost and enhance scalability, LELANTE utilizes model distillation using a foundational LLM. In experiments across 390 test cases spanning 10 popular Android applications, LELANTE achieved a 73% test execution success rate. Our results demonstrate that LLMs can effectively bridge the gap between natural language test case description and automated execution, making mobile testing more scalable and adaptable. |
| title | LELANTE: LEveraging LLM for Automated ANdroid TEsting |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2504.20896 |