"Let’s ask what AI thinks then!": Using LLMs for Collaborative Problem-Solving in Virtual Environments

Integrating Large Language Models (LLMs) in immersive virtual environments presents a significant opportunity for enhancing collaborative problem-solving. As online communication becomes increasingly embedded in both our personal and professional lives, tools like LLMs show significant potential to facilitate real-time interaction and improve group dynamics including problem-solving. Leveraging the capabilities of virtual environments, combined with LLMs, can provide engaging, immersive and interactive experiences that are different from those found in traditional settings. This paper explores how these technologies can effectively be utilized to foster collaborative problem-solving in virtual environments, examining both the benefits and challenges of this integration. Finally, this paper proposes a framework for developing applications with integrated LLMs.