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

2026-03-26

AI Summary

Existing approaches struggle to automatically verify the reliability of web functionalities in open environments, particularly due to the lack of modeling logical constraints. To address this gap, this work presents WebTestBench, the first systematic benchmark for end-to-end automated web testing, which decomposes the testing task into two cascaded subtasks: check generation and defect detection. The authors further introduce WebTester, a baseline framework that leverages large language models to generate test checks, identify defects, simulate long-horizon interactions, and perform multi-dimensional evaluation. Experimental results demonstrate that current agents still exhibit significant deficiencies in test completeness, defect detection rates, and stability in long-horizon interactions, indicating a substantial gap before industrial deployment becomes feasible.

Technology Category

• Knowledge Representation and Reasoning: Computational Complexity of Reasoning
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization

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.

Problem

• automated web testing
• computer-use agents
• latent logical constraints
• end-to-end evaluation
• web functionality verification

Innovation

• WebTestBench
• end-to-end automated web testing
• checklist generation
• defect detection
• latent logical constraints