What question did this study set out to answer?

The research aims to enhance software testing by integrating large language models with rigorous testing methodologies.

March 6, 20260 citationsOpen Access

A Business Process-Centric Approach for LLM-Driven Functional Test Generation

PMPhu Trong Mai TNTung Son Ngo NLNgoc Hai Le

Key Points

The research aims to enhance software testing by integrating large language models with rigorous testing methodologies.
Developed a hybrid framework combining LLMs and graph-based navigation.
Utilized combinatorial optimization techniques such as Pairwise and Boundary Value Analysis (BVA).
Focused on generating tests for long-horizon business processes while preserving context.
Achieved high-fidelity test generation for complex systems.
Maintained state continuity during the testing process.
Improved the effectiveness of functional testing in industrial applications.

Abstract

IntelliTest is a hybrid framework designed to bridge the gap between the semantic reasoning of Large Language Models (LLMs) and the logical rigor required for industrial-grade software testing. By combining LLMs with graph-based navigation and combinatorial optimization (Pairwise and BVA), IntelliTest achieves high-fidelity test generation for complex, long-horizon business processes while maintaining context and state continuity.

AIに質問

Bookmark

View Full Paper