Does Persona Make LLMs K-pop Fans? A Pilot Study of LLM-Based Online Concert Audience Agents
arXiv:2606.07837v1 Announce Type: cross Abstract: A concert is a collective experience, but recorded performance videos are typically watched alone, stripping away the shared audience presence that makes concerts feel eventful. We investigate whether persona-based LLM audience agents can recreate aspects of this collective experience by generating real-time fan chat alongside a K-pop performance video. We present a multi-agent system in which ten LLM agents react through live-chat messages, comparing a persona-conditioned audience (each agent assigned a distinct fan identity, bias, and chat st
The proliferation of advanced LLMs and multi-agent systems allows for novel applications in simulating human-like interactions, leading to explorations like recreating collective experiences.
This pilot study demonstrates a tangible application for AI agents in creating engaging, simulated social environments, potentially impacting entertainment consumption and digital interaction models.
The ability to generate dynamic, persona-driven audience interactions for recorded content could transform how audiences engage with media, moving from passive viewing to interactive simulated social events.
- · AI agent developers
- · Entertainment platforms
- · Digital content creators
- · Metaverse developers
- · Traditional passive media formats
Individual consumers experience recorded media with enhanced, simulated social presence and interaction.
Content platforms invest in and integrate AI-driven audience agents to increase user engagement and retention.
The definition of 'audience' expands to include sophisticated AI entities, blurring lines between human and artificial participation in digital events.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI