The increasing complexity of modern software systems has made the maintenance of software testing artifacts—such as requirements traceability, outdated test cases, and duplicate bug reports—a significant challenge for software engineers. Large Language Models (LLMs) present a novel opportunity to address these issues by automating routine tasks, reducing redundancy, and improving artifact consistency. This research aims to explore how LLMs can support practitioners in managing and maintaining these testing artifacts by generating traceability links, identifying outdated or duplicated items, and offering intelligent updates. Additionally, the project will investigate the use of chatbot interfaces powered by LLMs to facilitate collaborative maintenance, enabling engineers to query, discuss, and refine testing artifacts in real time. By integrating LLMs into the software testing lifecycle, this research seeks to enhance productivity, reduce errors, and promote seamless collaboration in software engineering teams.