Behavior Trees (BTs) enable dynamic and strategic gameplay by controlling non-player characters (NPCs) in video games, but their construction and iterative refinement remain time-consuming and technically demanding for game developers. This project explores the integration of Large Language Models (LLMs) within Unreal Engine 5 as a tool to automatically generate BTs from natural language prompts, thereby reducing the complexity of designing game AI and accelerating the production pipeline. In order to choose the adapted model in terms of coherence and practicability for local integration, multiple models were benchmarked. Results revealed that models under 2.5 GB provided the best trade-off between performance and output quality. The LLaMA 3.2 3B Instruct quantized model was found to be particularly suitable. In this study, we have thus developed a tool based on the Llama-Unreal Plugin to implement a local LLM into the engine. A custom prompt interface was implemented in the editor, allowing users to submit natural language inputs. The model responds with an XML description of the BT, which is then parsed and instantiated as a native BT asset in Unreal Engine. The XML schema was carefully designed to accommodate different node types (tasks, composites, decorators). The implemented system was tested with simple NPC behaviors like seeking and chasing the player for a guardian, or like a boss fight sequence for a dragon. It successfully produced functional BTs from simple prompts in various gameplay scenarios. Early results have shown how LLMs can streamline the creation of Game AI. The system could be extended to support more complex and hierarchical BTs, improve error handling in XML parsing, and integrate with other game engines such as Unity or Godot.

abstract- Various research studies, with contradictory results, indicate that tempo synchronization affects player performance differently depending on whether it is aligned with gameplay or player actions. To test this hypothesis, this demo presents a customized 3D video game with a dynamic audio system, allowing separate synchronization with game states or player decisions. Empirical tests have shown that the audio is well synchronized with in-game events. Moreover, the created game is intended to offer an immersive setting suitable for examining the diverse effects of musical alignment on player abilities.

This demo presents an educational e-learning module that teaches emotion regulation to medical students in a 3D virtual environment. The scenario focuses on the pressure and stress experienced by students when studying for an exam. The survey results based on 50 university students have shown that the immersive tool is effective to elicit stress and anxiety emotions. Although the majority of students were able to regulate their emotions, half of them used inappropriate strategies to manage their negative emotions.

The practitioner-patient relationship (PPR) is essential to the improvement of health care services for patients suffering from cognitive impairments. However, teaching medical students how to develop a healthy PR using conventional approaches is difficult, due to the lack of real context. To address this issue, TeachMod presents a new educational game-based course that offers an interactive and immersive learning through two different scenarios of psychiatric consultations. The course was tested and evaluated with 64 undergraduate students who expressed a positive attitude to the game design and its pedagogical content. The survey results indicate that the course is sufficiently intuitive to foster learning the fundamentals of an ethical and appropriate PPR.

Gaze and attention guidance is the most important challenge in virtual reality (VR) games because they affect comprehension, playability and immersion in the interactive environment. In this work, we propose an intuitive game-design approach to subtly guide the user’s attention in a new custom VR game. The results of the survey show the potential of this approach to enhance the VR experience that leading to a high rate of comprehension and focus on game mechanics.