Search papers, labs, and topics across Lattice.
This paper empirically evaluates the effectiveness of large language models (LLMs) in automated model-based test generation, comparing their performance against the established GraphWalker tool and its algorithms. The study reveals that LLMs can significantly optimize test paths and reduce step sizes, demonstrating their potential to enhance scalability in industrial model-based testing applications. By testing across various applications of increasing complexity, the findings suggest that LLMs could be a game-changer in software testing methodologies.
LLMs can optimize model-based test generation, outperforming traditional tools in both path efficiency and scalability.
Large language models have shown strong potential for software engineering tasks, particularly software testing. Model-based testing (MBT) is a software testing technique. To address the broad scalability challenge for industrial adoption of MBTs, our paper presents an empirical evaluation of Large Language Models (LLMs) for automated model-based test generation, compared with a state-of-the-art model-based testing tool (GraphWalker) and its built-in algorithms (random and quick random for edge and vertex coverage settings). Our evaluation indicates strong potential to optimize and shorten test paths and step sizes using the recent five state-of-the-art LLMs (GPT-5.1, GPT-5.2, Claude Opus 4.5, Claude Sonnet 4.5, and Gemini 2.5 Pro) against four GraphWalker models (two web applications (Parabank and Testinium) and two hardware applications (TLC and RISC-V) ) of escalating complexity.
