What question did this study set out to answer?

The study aims to develop a framework for automated web-form-test generation using large language models.

February 16, 2026

Large Language Models for Automated Web-Form-Test Generation: An Empirical Study — RCR Report

Key Points

The study aims to develop a framework for automated web-form-test generation using large language models.
Developed a framework that integrates HTML pruning, context construction, and prompt design.
Constructed three prompt types to guide test generation from HTML: RH-P, LH-P, and PH-P.
Implemented a standardized LLM communication module for API interactions.
PH-P achieved a higher successfully-submitted rate compared to RH-P and LH-P.
The framework was tested using public API models.
Source code, dataset subset, and relevant scripts were made available for replication.

Abstract

This report presents a framework that enables the reproduction and extension of our empirical evaluations using Large Language Models (LLMs) for automated web-form-test generation. The framework includes HTML pruning , context construction , prompt design , LLM communication , and web-form-test insertion . It involves the construction of three types of prompts (from HTML) to guide the test generation: Raw HTML for Task Prompt (RH-P); LLM-Processed HTML for Task Prompt (LH-P); and Parser-Processed HTML for Task Prompt (PH-P). The framework provides an LLM communication module that standardizes interactions with provider Application Programming Interfaces (APIs). Our study utilized public-API models and demonstrated that PH-P consistently achieved a higher successfully-submitted rate (SSR) than RH-P and LH-P. To support the replication of our work, we have released the source code, a dataset subset, and the relevant scripts.

Ask AI

Helpful

Bookmark