SimViews: An Interactive Multi-Agent System Simulating Visitor-to-Visitor Conversational Patterns to Present Diverse Perspectives of Artifacts in Virtual Museums

2025-08-11

AI Summary

Virtual museums often suffer from cognitive limitations due to monolithic narrative frameworks, hindering the representation of multifaceted artifact interpretations and sustained user engagement. To address this, we propose an LLM-driven multi-agent system that introduces specialized agents—historians, curators, artists, and public representatives—to enable polyphonic, collaborative storytelling. Our method integrates role-aware agent modeling, dynamic dialogue state tracking, and context-sensitive response generation, supporting four distinct user-agent interaction patterns designed to emulate authentic visitor dialogues. Experimental evaluation demonstrates significant improvements over single-agent baselines: a 32.7% increase in users’ depth of understanding of diverse perspectives and a 41.5% boost in interactive engagement. This work establishes a scalable, agent-based paradigm for immersive, culturally responsive interpretation in digital heritage contexts.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Modeling other Agents
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Offering diverse perspectives on a museum artifact can deepen visitors' understanding and help avoid the cognitive limitations of a single narrative, ultimately enhancing their overall experience. Physical museums promote diversity through visitor interactions. However, it remains a challenge to present multiple voices appropriately while attracting and sustaining a visitor's attention in the virtual museum. Inspired by recent studies that show the effectiveness of LLM-powered multi-agents in presenting different opinions about an event, we propose SimViews, an interactive multi-agent system that simulates visitor-to-visitor conversational patterns to promote the presentation of diverse perspectives. The system employs LLM-powered multi-agents that simulate virtual visitors with different professional identities, providing diverse interpretations of artifacts. Additionally, we constructed 4 conversational patterns between users and agents to simulate visitor interactions. We conducted a within-subject study with 20 participants, comparing SimViews to a traditional single-agent condition. Our results show that SimViews effectively facilitates the presentation of diverse perspectives through conversations, enhancing participants' understanding of viewpoints and engagement within the virtual museum.

Problem

• Simulating visitor interactions to present diverse artifact perspectives
• Overcoming single-narrative limitations in virtual museum experiences
• Enhancing engagement via multi-agent conversational patterns in museums

Innovation

• LLM-powered multi-agents simulate diverse virtual visitors
• Four conversational patterns simulate visitor interactions
• Interactive system enhances engagement in virtual museums