Conversational agents in virtual environments are an established approach for immersively conveying the information and narratives of museums and cultural heritage while expanding their accessibility to a wider and remote audience. The rapid development of large language models and text-to-speech technologies has raised the agents’ conversational level significantly, which allows their use for proactive guidance of visitors. This raises the vital question of how such agents should be visually represented to promote Knowledge transfer in immersive virtual environments. In this paper, we compared two representation concepts for agent embodiments in the context of a virtual museum by examining a stylized humanoid guide and a novel animism-based approach that enables users to talk to exhibited objects. Our work addresses the challenge of naturally introducing a virtual educational environment to users and encouraging their interest and engagement with the content. A user study $(N=29)$ revealed high usability and similar presence scores for the experience with each of the embodiments. A majority of participants showed a preference for the animated objects. In terms of user experience, they evoked significant stimulation and high levels of engagement. Our results suggest that agents that show emotions through appropriate word choice influence engagement levels. Based on our findings, we recommend humanoid guides for delivering general background information, while animated objects promote detailed questions about their own stories and a more stimulating exchange.

Virtual environments with an ambient natural interface that allows to retrieve information for learning about the environment are a promising combination for implementing engaging virtual exhibitions. As a step towards better understanding search behavior in such exhibitions, this paper contributes the data from an exploratory study with participants asking questions on a real-world historical room, the Gropiuszimmer at the Weimar Bauhaus, while being on an “online virtual tour” through the room. The dataset comprises 849 manually categorized questions (557 in English, 292 in German) from 63 participants combined with a detailed interaction log, which allows replaying each session (29 hours total). The presented dataset and analyses aim to provide researchers and practitioners with a starting point to develop in-depth studies and prototypical systems.