An Explainable Emotion Alignment Framework for LLM-Empowered Agent in Metaverse Service Ecosystem

TL;DR

This paper introduces an explainable emotion alignment framework for LLM-based agents in the Metaverse, enhancing their ability to integrate factual data and improve social interactions within service ecosystems.

Contribution

It presents a novel framework that systematically aligns relational facts and emotions in LLM agents, addressing ethical and knowledge integration challenges in the Metaverse.

Findings

Improved social emergence in simulation experiments

Enhanced factual and emotional alignment in agents

Better bridging of virtual and real-world services

Abstract

Metaverse service is a product of the convergence between Metaverse and service systems, designed to address service-related challenges concerning digital avatars, digital twins, and digital natives within Metaverse. With the rise of large language models (LLMs), agents now play a pivotal role in Metaverse service ecosystem, serving dual functions: as digital avatars representing users in the virtual realm and as service assistants (or NPCs) providing personalized support. However, during the modeling of Metaverse service ecosystems, existing LLM-based agents face significant challenges in bridging virtual-world services with real-world services, particularly regarding issues such as character data fusion, character knowledge association, and ethical safety concerns. This paper proposes an explainable emotion alignment framework for LLM-based agents in Metaverse Service Ecosystem. It aims to integrate factual factors into the decision-making loop of LLM-based agents, systematically demonstrating how to achieve more relational fact alignment for these agents. Finally, a simulation experiment in the Offline-to-Offline food delivery scenario is conducted to evaluate the effectiveness of this framework, obtaining more realistic social emergence.