Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

An efficient approach to represent enterprise web application structure using Large Language Model in the service of Intelligent Quality Engineering

Zaber Al Hassan Ayon, Gulam Husain, Roshankumar Bisoi, Waliur Rahman, Dr Tom Osborn

TL;DR

Enterprise web applications are deeply complex, requiring scalable, autonomous quality engineering that can reason about architecture and interactions. The authors introduce a hierarchical, DOM-based representation optimized for few-shot learning with LLMs to drive intelligent QE across a five-phase pipeline from DOM analysis to test reporting. They demonstrate the approach on Swag Labs and MediBox, showing context-aware test generation and execution with substantial execution success and high relevance of test cases. The work promises reduced manual maintenance and improved QA coverage at scale, enabling more efficient autonomous testing in enterprise environments.

Abstract

This paper presents a novel approach to represent enterprise web application structures using Large Language Models (LLMs) to enable intelligent quality engineering at scale. We introduce a hierarchical representation methodology that optimizes the few-shot learning capabilities of LLMs while preserving the complex relationships and interactions within web applications. The approach encompasses five key phases: comprehensive DOM analysis, multi-page synthesis, test suite generation, execution, and result analysis. Our methodology addresses existing challenges around usage of Generative AI techniques in automated software testing by developing a structured format that enables LLMs to understand web application architecture through in-context learning. We evaluated our approach using two distinct web applications: an e-commerce platform (Swag Labs) and a healthcare application (MediBox) which is deployed within Atalgo engineering environment. The results demonstrate success rates of 90\% and 70\%, respectively, in achieving automated testing, with high relevance scores for test cases across multiple evaluation criteria. The findings suggest that our representation approach significantly enhances LLMs' ability to generate contextually relevant test cases and provide better quality assurance overall, while reducing the time and effort required for testing.

An efficient approach to represent enterprise web application structure using Large Language Model in the service of Intelligent Quality Engineering

TL;DR

Enterprise web applications are deeply complex, requiring scalable, autonomous quality engineering that can reason about architecture and interactions. The authors introduce a hierarchical, DOM-based representation optimized for few-shot learning with LLMs to drive intelligent QE across a five-phase pipeline from DOM analysis to test reporting. They demonstrate the approach on Swag Labs and MediBox, showing context-aware test generation and execution with substantial execution success and high relevance of test cases. The work promises reduced manual maintenance and improved QA coverage at scale, enabling more efficient autonomous testing in enterprise environments.

Abstract

This paper presents a novel approach to represent enterprise web application structures using Large Language Models (LLMs) to enable intelligent quality engineering at scale. We introduce a hierarchical representation methodology that optimizes the few-shot learning capabilities of LLMs while preserving the complex relationships and interactions within web applications. The approach encompasses five key phases: comprehensive DOM analysis, multi-page synthesis, test suite generation, execution, and result analysis. Our methodology addresses existing challenges around usage of Generative AI techniques in automated software testing by developing a structured format that enables LLMs to understand web application architecture through in-context learning. We evaluated our approach using two distinct web applications: an e-commerce platform (Swag Labs) and a healthcare application (MediBox) which is deployed within Atalgo engineering environment. The results demonstrate success rates of 90\% and 70\%, respectively, in achieving automated testing, with high relevance scores for test cases across multiple evaluation criteria. The findings suggest that our representation approach significantly enhances LLMs' ability to generate contextually relevant test cases and provide better quality assurance overall, while reducing the time and effort required for testing.
Paper Structure (29 sections, 1 equation, 1 figure, 4 tables)

This paper contains 29 sections, 1 equation, 1 figure, 4 tables.

Table of Contents

  1. Introduction
  2. Background and Related Work
  3. Methodology
  4. Phase 1: Comprehensive DOM Analysis and Data Structuring
  5. Phase 2: Multi-Page Analysis and Site-Wise Synthesis
  6. Phase 3: Contextual and Relevant Test Suite Generation and Validation
  7. Phase 4: Test Suite Execution
  8. Phase 5: Test Report and Analysis
  9. Experiment
  10. Objectives
  11. Experimental Setup
  12. Scope of Experiments
  13. Web Scraping and Data Extraction
  14. Site Analysis and Hierarchical Representation
  15. Automated Test Case Generation Using LLMs
  16. ...and 14 more sections

Figures (1)

  • Figure 1: Overall phase flow