Dynamic Gimmick Learning for Navigation Agents in Social VR Through User-Agent Dialogue

Atsuya Matsumoto; Hikari Yanagawa; Yuichi Hiroi; Yuji Hatada; Takuji Narumi; Takefumi Hiraki

doi:10.1109/ismar-adjunct68609.2025.00120

Home
Search
Dynamic Gimmick Learning for Navigation Agents in Social VR Through User-Agent Dialogue

https://doi.org/10.1109/ismar-adjunct68609.2025.00120

Dynamic Gimmick Learning for Navigation Agents in Social VR Through User-Agent Dialogue

Oct 8, 2025
Atsuya Matsumoto +5 more

Listen

Abstract
Literature Map
References
Similar Papers

Abstract

User-generated interactive mechanisms ("gimmicks") in metaverse platforms offer unique experiences, but their complexity hinders player exploration. Existing navigation agents, reliant on static metadata, cannot comprehend these dynamic gimmicks. We propose the "Conversational Knowledge Acquisition Loop," a method for agents to dynamically learn gimmicks through player conversation. A preliminary study showed that our agent successfully acquired knowledge via conversation and applied it to solve analogous gimmicks.