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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wan, Zhenyu, Chen, Gong, Huang, Qing, Xie, Xiaoyuan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914474171039744
author Wan, Zhenyu
Chen, Gong
Huang, Qing
Xie, Xiaoyuan
author_facet Wan, Zhenyu
Chen, Gong
Huang, Qing
Xie, Xiaoyuan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_13559
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle WebMAC: A Multi-Agent Collaborative Framework for Scenario Testing of Web Systems
Wan, Zhenyu
Chen, Gong
Huang, Qing
Xie, Xiaoyuan
Software Engineering
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.
title WebMAC: A Multi-Agent Collaborative Framework for Scenario Testing of Web Systems
topic Software Engineering
url https://arxiv.org/abs/2604.13559