WebMAC: A Multi-Agent Collaborative Framework for Scenario Testing of Web Systems

TL;DR

WebMAC is a multi-agent framework that enhances scenario testing of web systems by completing, transforming, and generating test scripts from natural language descriptions, improving success rates and efficiency.

Contribution

It introduces a multi-agent collaborative approach that addresses limitations of existing LLM-based testing methods by completing and transforming test scenarios more effectively.

Findings

WebMAC improves test script success rate by 30%-60%.

WebMAC increases testing efficiency by 29%.

WebMAC reduces token consumption by 47.6%.

Abstract

Scenario testing is an important technique for detecting errors in web systems. Testers draft test scenarios and convert them into test scripts for execution. Early methods relied on testers to convert test scenarios into test scripts. Recent LLM-based scenario testing methods can generate test scripts from natural language descriptions of test scenarios. However, these methods are not only limited by the incompleteness of descriptions but also overlook test adequacy criteria, making it difficult to detect potential errors. To address these limitations, this paper proposes WebMAC, a multi-agent collaborative framework for scenario testing of web systems. WebMAC can complete natural language descriptions of test scenarios through interactive clarification and transform adequate instantiated test scenarios via equivalence class partitioning. WebMAC consists of three multi-agent modules, responsible respectively for completing natural language descriptions of test scenarios, transforming test scenarios, and converting test scripts. We evaluated WebMAC on four web systems. Compared with the SOTA method, WebMAC improves the execution success rate of generated test scripts by 30%-60%, increases testing efficiency by 29%, and reduces token consumption by 47.6%. Furthermore, WebMAC can effectively detect more errors in web systems.