Model-Based Testing (MBT) enables the automated generation of test suites from requirement models. However, the frequent changes in agile development often lead teams to indiscriminately discard existing test cases, undermining the efficiency of Test Case Maintenance (TCM). This practice results in the loss of valuable test artifacts and escalates costs due to redundant test generation. Previous research has explored test case reuse through distance functions, but this strategy often suffers from low precision and misclassification. These issues lead to an excessive number of test cases being incorrectly considered reusable. In this paper, we investigate the use of Large Language Models (LLMs) to improve test case management. Through an empirical study on two industrial systems, we analyzed the performance of 13 well-known LLMs in classifying the impact of use case edits using CoT (Chain of Thought)/ToT (Tree of Thought) prompting and Naive-RAG strategies. Our findings indicate that seven of these models effectively reduced the unnecessary discarding of test cases by accurately identifying high-impact requirement changes, achieving a 7% improvement over distance functions. This resulted in a more precise, reliable, and efficient TCM solution within MBT. However, compared to distance-function-based strategies, LLMs exhibited slightly lower recall, performing 6% worse in test case reuse and reduction information loss.

Model-Based Testing (MBT) can be a valuable tool for software testing, automating test generation from the System Under Test (SUT) models and making the testing process systematic. However, it is common for models to undergo changes during the software lifecycle, which requires adaptive and robust testing strategies. As models evolve, the generated MBT suites require maintenance. While some tests may remain usable, others may become obsolete or require revision. In such scenarios, it is common for parts of an MBT suite to be discarded due to model changes, resulting in additional costs and hindering bug traceability. Therefore, maintaining MBT suites poses a significant challenge to their practical use. This paper presents a Systematic Literature Review (SLR) identifying predominant practices related to MBT suite maintenance, with a focus on strategies for reducing test case discard. The findings reveal that while reuse can prevent the loss of valuable test information, it is fundamentally driven by changes in requirement models, hinging on syntactic differences and the specific constructs of each model's formalism, highlighting the critical role of semantic deepening to minimize test case discard in Test Case Maintenance (TCM) with MBT approaches.