The Potential of LLMs in Automating Software Testing: From Generation to Reporting
Betim Sherifi, Khaled Slhoub, Fitzroy Nembhard
TL;DR
This work addresses the inefficiency of manual software testing by presenting an LLM-powered, multi-agent framework that automates test generation, execution, and reporting. The methodology couples a Software Testing Agent with LLMs to generate unit tests, visualize call graphs, and produce comprehensive PDFs within a development environment. Empirical evaluations on four projects (Python and Java) demonstrate high test coverage and generally robust performance, highlighting the framework's potential to reduce human intervention and accelerate testing workflows. Limitations include prompt ambiguity and compilation errors in Java, with future directions targeting broader test types, language support, and enhanced visualization to improve scalability and reliability.
Abstract
Having a high quality software is essential in software engineering, which requires robust validation and verification processes during testing activities. Manual testing, while effective, can be time consuming and costly, leading to an increased demand for automated methods. Recent advancements in Large Language Models (LLMs) have significantly influenced software engineering, particularly in areas like requirements analysis, test automation, and debugging. This paper explores an agent-oriented approach to automated software testing, using LLMs to reduce human intervention and enhance testing efficiency. The proposed framework integrates LLMs to generate unit tests, visualize call graphs, and automate test execution and reporting. Evaluations across multiple applications in Python and Java demonstrate the system's high test coverage and efficient operation. This research underscores the potential of LLM-powered agents to streamline software testing workflows while addressing challenges in scalability and accuracy.