CompanionCast: Toward Social Collaboration with Multi-Agent Systems in Shared Experiences

TL;DR

CompanionCast is a framework that enables multiple AI agents to collaboratively enhance social experiences during shared media consumption by improving social presence and emotional sharing.

Contribution

It introduces a novel multi-agent system architecture with multimodal event detection and spatial audio to foster authentic social interactions in shared experiences.

Findings

Significantly increased perceived social presence during shared viewing.

Enhanced emotional sharing among participants with CompanionCast.

Validated effectiveness through pilot studies with soccer fans.

Abstract

Shared experiences are fundamental to social connection, yet media consumption is increasingly solitary. While AI companions offer real-time reactions and emotional regulation, existing systems either rely on single-agent designs or lack the social awareness and multi-party interaction required to replicate authentic group dynamics. We present CompanionCast, a general framework for orchestrating multiple specialized AI agents as social collaborators within a live shared context. CompanionCast integrates multimodal event detection, rolling context caching for improved grounding, and spatial audio to enhance co-presence. We validate CompanionCast through sports viewing, a domain with rich dynamics and strong social traditions. Pilot studies with soccer fans demonstrate that CompanionCast significantly improves perceived social presence and emotional sharing compared to solitary viewing. We conclude by discussing implications and open challenges for multi-agent systems as social collaborators in shared experiences.