IRL Dittos: Embodied Multimodal AI Agent Interactions in Open Spaces

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Seonghee, Ford, Denae, Tang, John, Junuzovic, Sasa, Roseway, Asta, Cutrell, Ed, Inkpen, Kori
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913812959985664
author Lee, Seonghee
Ford, Denae
Tang, John
Junuzovic, Sasa
Roseway, Asta
Cutrell, Ed
Inkpen, Kori
author_facet Lee, Seonghee
Ford, Denae
Tang, John
Junuzovic, Sasa
Roseway, Asta
Cutrell, Ed
Inkpen, Kori
contents We introduce the In Real Life (IRL) Ditto, an AI-driven embodied agent designed to represent remote colleagues in shared office spaces, creating opportunities for real-time exchanges even in their absence. IRL Ditto offers a unique hybrid experience by allowing in-person colleagues to encounter a digital version of their remote teammates, initiating greetings, updates, or small talk as they might in person. Our research question examines: How can the IRL Ditto influence interactions and relationships among colleagues in a shared office space? Through a four-day study, we assessed IRL Ditto's ability to strengthen social ties by simulating presence and enabling meaningful interactions across different levels of social familiarity. We find that enhancing social relationships depended deeply on the foundation of the relationship participants had with the source of the IRL Ditto. This study provides insights into the role of embodied agents in enriching workplace dynamics for distributed teams.
format Preprint
id arxiv_https___arxiv_org_abs_2504_21347
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle IRL Dittos: Embodied Multimodal AI Agent Interactions in Open Spaces
Lee, Seonghee
Ford, Denae
Tang, John
Junuzovic, Sasa
Roseway, Asta
Cutrell, Ed
Inkpen, Kori
Artificial Intelligence
Human-Computer Interaction
H.5.2; I.2.9
We introduce the In Real Life (IRL) Ditto, an AI-driven embodied agent designed to represent remote colleagues in shared office spaces, creating opportunities for real-time exchanges even in their absence. IRL Ditto offers a unique hybrid experience by allowing in-person colleagues to encounter a digital version of their remote teammates, initiating greetings, updates, or small talk as they might in person. Our research question examines: How can the IRL Ditto influence interactions and relationships among colleagues in a shared office space? Through a four-day study, we assessed IRL Ditto's ability to strengthen social ties by simulating presence and enabling meaningful interactions across different levels of social familiarity. We find that enhancing social relationships depended deeply on the foundation of the relationship participants had with the source of the IRL Ditto. This study provides insights into the role of embodied agents in enriching workplace dynamics for distributed teams.
title IRL Dittos: Embodied Multimodal AI Agent Interactions in Open Spaces
topic Artificial Intelligence
Human-Computer Interaction
H.5.2; I.2.9
url https://arxiv.org/abs/2504.21347