Work

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

Year: 2024

Type: conference-paper

Abstract: 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.

Source: IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)

DOI: 10.1109/ismar-adjunct64951.2024.00048

Authors: Esen Küçüktütüncü, Lisa Izzouzi

Institutions: Universitat de Barcelona, University of London, University College London

Language: English

Topic: Virtual Reality Applications and Impacts

Subfield: Human-Computer Interaction

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: European Commission

Awards: G434337789, GuestXR: A Machine Learning Agent for Social Harmony in eXtended Reality