CoEmpaTeam: Enhancing Cognitive Empathy using LLM-based Avatars and Dynamic Role Play in Virtual Reality

2026-03-17

AI Summary

In performance-oriented societies, cognitive empathy is progressively declining yet remains difficult to perceive and train, leading to a lack of effective interventions. This study proposes a novel training system that integrates large language models (LLMs) with virtual reality (VR), wherein LLM-driven virtual avatars endowed with customizable personality traits engage users in dynamic role-playing scenarios to facilitate immersive perspective-taking. By uniquely combining personalized personality modeling with interactive VR, the approach establishes a transferable paradigm for cognitive empathy training applicable to real-world social contexts. A three-phase, two-week longitudinal experiment with 32 participants, complemented by diary studies, demonstrates significant improvements in cognitive empathy, with most participants reporting successful transfer of acquired skills to everyday social interactions.

Technology Category

• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Humans and AI: Game Design — Virtual Humans, NPCs and Autonomous Characters
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Cognitive empathy, the ability to understand others' perspectives, is essential for effective communication, reducing biases, and constructive negotiation. However, this skill is declining in a performance-driven society, which prioritizes efficiency over perspective-taking. Here, the training of cognitive empathy is challenging because it is a subtle, hard-to-perceive soft skill. To address this, we developed CoEmpaTeam, a VR-based system that enables users to train their cognitive empathy by using LLM-driven avatars with different personalities. Through dynamic role play, users actively engage in perspective-taking, experiencing situations through another person's eyes. CoEmpaTeam deploys three avatars who significantly differ in their personality, validated by a technical evaluation and an online experiment (n=90). Next, we evaluated the system through a lab experiment with 32 participants who performed three sessions across two weeks, followed by a one-week diary study. Our results showed a significant increase in cognitive empathy, which, according to participants, transferred into their real lives.

Problem

• cognitive empathy
• soft skills
• perspective-taking
• empathy training
• social cognition

Innovation

• LLM-based avatars
• virtual reality
• cognitive empathy
• dynamic role play
• perspective-taking