Problems related to the quality of games, whether on the initial release or after updates, can lead to player dissatisfaction, media attention, and potential financial setbacks. These issues can stem from software bugs, performance bottlenecks, or security vulnerabilities. Despite these challenges, game developers often rely on manual playtesting, highlighting the need for more robust and automated processes in game development. This research explores the application of Large Language Models (LLMs) to automate the creation of unit tests in game development, focusing on strongly typed programming languages such as C++ and C#, which are widely used in the industry. The study focuses on fine-tuning Code Llama, an advanced code generation model, to address common scenarios in game development, including game engines and specific APIs or backends. Although the prototyping and evaluations primarily took place within the Unity game engine, the proposed methods can be adapted to other internal or publicly available solutions. The evaluation results demonstrate these methods’ effectiveness in improving existing unit test suites or automatically generating new tests based on natural language descriptions of class contexts and targeted methods.

By using Robotic Process Automation (RPA), repetitive processes in companies can be automated and executed with intelligent software agents. These agents are able to run such processes without human effort and with less error-proneness. RPA has gained significant traction in recent years and is being used by many companies to reduce internal costs and achieve a higher return on investment (ROI). In our literature review, we found that there is a gap in the testability of RPA workflows. In this paper, we focus on addressing this gap using concolic execution (also referred to as online symbolic execution in the literature). First, we explore how previous work in the literature on concolic execution can be reused for the RPA domain and we implement a prototype. Then, we evaluate our open source solution for adapting concolic execution to the RPA context, using real-world use cases and best practices.