ResearchPod Summary
This study investigates whether assigning distinct personas to LLM agents can recreate the sense of collective presence typically missing from asynchronous online concert viewing. The authors developed a multi-agent system where ten LLM agents generate real-time chat reactions to a K-pop performance video. They compared a persona-conditioned condition—where each agent was assigned a unique fan identity, bias, and chat style—against a no-persona baseline where agents lacked individual traits. The study used a within-subjects pilot with 11 K-pop fans to evaluate both model-level output quality and user-level subjective experience.
Persona conditioning successfully achieved its technical goal: it produced highly differentiated agent behaviors, reduced repetitive chat patterns, and increased overall output diversity. Participants explicitly recognized the persona-conditioned audience as more natural than the baseline. However, this increased naturalness failed to improve the users' sense of social connectedness, engagement, or affective response. The quantitative results showed no significant differences in these metrics between the two conditions, suggesting that while the agents appeared more realistic, they did not foster a more meaningful collective experience.
This research highlights a critical gap between the technical performance of AI agents and their ability to facilitate meaningful human social experiences. The authors suggest that online concert chat functions more as a collective monologue than an interpersonal dialogue. Consequently, simply making agents appear more human-like through persona prompting is insufficient; true collective experience may require deeper alignment between AI behavior, specific fandom identities, and the cultural expectations of the audience. The study underscores the need for domain-specific, culturally situated evaluation when designing AI agents for social contexts.
Alex: Welcome to another episode of ResearchPod. Today, we're looking at a paper that tackles a very specific, modern problem: how to make watching a concert video alone feel like you're actually in a crowd.
Sam: Right. The study, titled "Does Persona Make LLMs K-pop Fans?", asks whether artificial intelligence can simulate a virtual audience for recorded K-pop performances. The central question is whether giving AI agents distinct personalities—like a super-fan or a lurker—actually makes the experience feel more meaningful to a human viewer.
Alex: So the paper is basically asking: if you fake a personality for each member of a digital crowd, is that enough to recreate the energy of a live show?
Sam: That's the core question. They're testing something they call "persona conditioning." Think of it like writing a character profile for each AI agent—giving it a favorite band member, a unique way of typing, a specific age and background. The goal is to find out whether those individual personalities matter more than just having a crowd of generic, identical voices.
Alex: And the problem they're solving is that when you watch a concert recording by yourself, something is missing. There's no electricity from the crowd.
Sam: Exactly. The researchers point out that at a live concert, the audience isn't just watching—they're participating. Synchronized cheers, shared reactions, that sense of being swept up in something together. When you watch a recording alone, that entire social layer disappears. The question is whether AI can rebuild it.
Alex: And the mechanism is assigning different identities to each AI agent?
Sam: Yes. They use a system of ten AI agents, each programmed with a specific persona. Think of it like casting a play. Instead of ten identical extras in the background, you cast ten distinct characters—the super-fan who's always excited, the lurker who only speaks when their favorite member appears on screen, the newcomer who's still learning the fandom's culture.
Alex: How do they actually get the AI to behave like these different characters?
Sam: They give each agent a structured set of instructions—a kind of personality document—that defines their age, background, and most importantly, their "bias." In K-pop culture, your bias is the specific member of a group you support most strongly. By embedding these traits into the agent's instructions, the AI is essentially forced to behave differently from the others.
AI-generated third-party summary by ResearchPod. Not official content or an endorsement by the paper authors or affiliated organizations.
Alex: So the AI isn't improvising—it's following a script for its personality.
Sam: Right. They also feed the agents "segment labels"—basically timestamps that tell each agent what's happening on stage at any given moment, like when the chorus kicks in or when a specific singer is featured. That way the agents react to the right things at the right time, rather than just generating random comments. It keeps the virtual crowd in sync with the performance.
Alex: But if ten agents are all trying to talk at once, doesn't it just collapse into noise?
Sam: That's actually a known failure mode they had to design around. It's called "output collapse"—when all the agents start saying the exact same thing, like a room full of people simultaneously shouting "Wow!" To prevent it, each agent gets a personal memory of what it said recently, so it doesn't just repeat itself. They also share a common chat log, so agents can see what the others—and the human viewer—are saying.
Alex: And how did they test whether any of this actually worked?
Sam: They ran a pilot study with eleven K-pop fans. Each participant watched the same four-minute performance twice: once with the persona-conditioned agents, and once with a baseline version where all the agents were identical. Afterward, they asked participants how connected they felt to the audience and how natural the experience seemed.
Alex: So did the personalized agents make fans feel more connected?
Sam: This is where the results become genuinely interesting. The persona-conditioned agents were rated as significantly more natural-feeling than the identical ones. Participants noticed they seemed more like real people. But—and this is the key finding—that increased naturalness didn't translate into stronger social connection or higher engagement. People could tell the agents felt more human, but they didn't feel more like part of a real community.
Alex: So the naturalness didn't actually produce a better social experience.
Sam: That's exactly it. The interviews pointed to something the researchers describe as a "collective monologue." In online K-pop concert chats, people aren't really having conversations with each other—they're expressing excitement simultaneously, like a stadium crowd cheering in unison. Everyone is broadcasting their own reaction, not responding to anyone else's.
Alex: Oh—so that's why the individual personas didn't matter as much? The fans weren't trying to make friends with specific AI agents. They were looking for the overall vibe of a crowd.
Sam: Exactly. What participants cared about was the collective atmosphere—the trends, the repetitive cheers, the shared energy of the fandom as a whole. Making an individual AI agent seem more human doesn't automatically create that sense of shared identity. The "soul" of the fandom, as one might put it, is a group property, not an individual one.
Alex: It's like being at a concert. You don't need to know the life story of the person standing next to you to feel the energy of the crowd. You just need to know you're both there for the same reason.
Sam: That's a useful way to frame it. The researchers conclude that meaningful participation in these spaces depends on shared cultural context. If you don't know the fandom's specific slang, or the history of the group, the AI crowd just feels like noise—no matter how realistic the individual agents seem.
Alex: So the vibe of the collective matters more than the realism of any single agent.
Sam: That's the takeaway. If we want AI audiences that genuinely foster a sense of community, the research suggests we need to focus on the collective dynamics of the fandom—not just on making individual agents seem more lifelike. It's a meaningful step toward understanding how technology might bridge the gap between watching something alone and feeling like you're experiencing it together.
Alex: That's a thought-provoking result—the thing that makes a crowd feel real isn't any one person in it, but the shared energy between all of them. Thanks for listening to ResearchPod.