Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

WebTestBench: Evaluating Computer-Use Agents towards End-to-End Automated Web Testing

Fanheng Kong, Jingyuan Zhang, Yang Yue, Chenxi Sun, Yang Tian, Shi Feng, Xiaocui Yang, Daling Wang, Yu Tian, Jun Du, Wenchong Zeng, Han Li, Kun Gai

Abstract

The emergence of Large Language Models (LLMs) has catalyzed a paradigm shift in programming, giving rise to "vibe coding", where users can build complete projects and even control computers using natural language instructions. This paradigm has driven automated webpage development, but it introduces a new requirement about how to automatically verify whether the web functionalities are reliably implemented. Existing works struggle to adapt, relying on static visual similarity or predefined checklists that constrain their utility in open-ended environments. Furthermore, they overlook a vital aspect of software quality, namely latent logical constraints. To address these gaps, we introduce WebTestBench, a benchmark for evaluating end-to-end automated web testing. WebTestBench encompasses comprehensive dimensions across diverse web application categories. We decompose the testing process into two cascaded sub-tasks, checklist generation and defect detection, and propose WebTester, a baseline framework for this task. Evaluating popular LLMs with WebTester reveals severe challenges, including insufficient test completeness, detection bottlenecks, and long-horizon interaction unreliability. These findings expose a substantial gap between current computer-use agent capabilities and industrial-grade deployment demands. We hope that WebTestBench provides valuable insights and guidance for advancing end-to-end automated web testing. Our dataset and code are available at https://github.com/friedrichor/WebTestBench.

WebTestBench: Evaluating Computer-Use Agents towards End-to-End Automated Web Testing

Abstract

The emergence of Large Language Models (LLMs) has catalyzed a paradigm shift in programming, giving rise to "vibe coding", where users can build complete projects and even control computers using natural language instructions. This paradigm has driven automated webpage development, but it introduces a new requirement about how to automatically verify whether the web functionalities are reliably implemented. Existing works struggle to adapt, relying on static visual similarity or predefined checklists that constrain their utility in open-ended environments. Furthermore, they overlook a vital aspect of software quality, namely latent logical constraints. To address these gaps, we introduce WebTestBench, a benchmark for evaluating end-to-end automated web testing. WebTestBench encompasses comprehensive dimensions across diverse web application categories. We decompose the testing process into two cascaded sub-tasks, checklist generation and defect detection, and propose WebTester, a baseline framework for this task. Evaluating popular LLMs with WebTester reveals severe challenges, including insufficient test completeness, detection bottlenecks, and long-horizon interaction unreliability. These findings expose a substantial gap between current computer-use agent capabilities and industrial-grade deployment demands. We hope that WebTestBench provides valuable insights and guidance for advancing end-to-end automated web testing. Our dataset and code are available at https://github.com/friedrichor/WebTestBench.

Paper Structure

This paper contains 27 sections, 7 equations, 8 figures, 11 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. WebTestBench
  4. Task Definition
  5. Data Construction
  6. Evaluation Metrics
  7. WebTester
  8. Experiments
  9. Settings
  10. Main Results
  11. Overall Performance.
  12. Fine-grained Analysis
  13. Oracle Setting
  14. Conclusion
  15. WebTestBench
  16. ...and 12 more sections

Figures (8)

  • Figure 1: Overview of WebTestBench construction.
  • Figure 2: An illustrative example from WebTestBench. The web application is built from a given development instruction, typically comprising multiple pages with rich interactive functionality. The benchmark provides a gold checklist across four quality dimensions: Functionality, Constraint, Interaction, and Content. Each test case is annotated with a binary Pass/Fail verdict.
  • Figure 3: Comparison of perfermance between the end-to-end (E2E) setting and the oracle setting for representative models. In the oracle setting, the gold checklist is directly provided to the defect detection agent, decoupling detection performance from checklist generation quality.
  • Figure 4: Performance comparison across different web complexity in the oracle setting.
  • Figure 5: An example illustrating how CUA interacts with a web application during defect detection.
  • ...and 3 more figures