When Nobody Around Is Real: Exploring Public Opinions and User Experiences On the Multi-Agent AI Social Platform

• URL: http://arxiv.org/abs/2601.18275v1
• Date: Mon, 26 Jan 2026 08:58:51 GMT
• Title: When Nobody Around Is Real: Exploring Public Opinions and User Experiences On the Multi-Agent AI Social Platform
• Authors: Qiufang Yu, Mengmeng Wu, Xingyu Lan,
• Abstract summary: A new genre of multi-agent social platforms has emerged, powered by large language models.<n>Social.AI deploys numerous AI agents that emulate human behavior, creating unprecedented bot-centric social networks.<n>While some user expectations were met, the AI-dominant social environment introduces distinct problems.
• Score: 5.133676030875285
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Powered by large language models, a new genre of multi-agent social platforms has emerged. Apps such as Social.AI deploy numerous AI agents that emulate human behavior, creating unprecedented bot-centric social networks. Yet, existing research has predominantly focused on one-on-one chatbots, leaving multi-agent AI platforms underexplored. To bridge this gap, we took Social.AI as a case study and performed a two-stage investigation: (i) content analysis of 883 user comments; (ii) a 7-day diary study with 20 participants to document their firsthand platform experiences. While public discourse expressed greater skepticism, the diary study found that users did project a range of social expectations onto the AI agents. While some user expectations were met, the AI-dominant social environment introduces distinct problems, such as attention overload and homogenized interaction. These tensions signal a future where AI functions not merely as a tool or an anthropomorphized actor, but as the dominant medium of sociality itself-a paradigm shift that foregrounds new forms of architected social life.

Related papers

• MoltNet: Understanding Social Behavior of AI Agents in the Agent-Native MoltBook [26.126469624250916]
  MoltNet is a large-scale empirical analysis of agent interaction on MoltBook.<n>We examine behavior along four dimensions: intent and motivation, norms and templates, incentives and behavioral drift, emotion and contagion.
  arXiv  Detail & Related papers  (2026-02-13T21:03:59Z)
• SI-Bench: Benchmarking Social Intelligence of Large Language Models in Human-to-Human Conversations [8.453848538355508]
  We introduce SI-Bench, a novel benchmark to evaluate aspects of social intelligence in large language models (LLMs)<n>Grounded in broad social science theories, SI-Bench contains 2,221 authentic multi-turn dialogues collected from a social networking application.<n>Experiments show that SOTA models have surpassed the human expert in process reasoning under complex social situations, yet they still fall behind humans in reply quality.
  arXiv  Detail & Related papers  (2025-10-27T10:21:46Z)
• Social Identity in Human-Agent Interaction: A Primer [37.39284422390363]
  Social identity theory (SIT) and social categorization theory (SCT) are two facets of the social identity approach (SIA) to understanding social phenomena.<n>SIT and SCT are models that describe and explain how people interact with one another socially.<n>The rise of increasingly social machines embedded in daily life has spurned efforts on understanding whether and how artificial agents can and do participate in SIA activities.<n>I provide a primer on SIA and extrapolate, through case studies and imagined examples, how SIT and SCT can apply to artificial social agents.
  arXiv  Detail & Related papers  (2025-08-12T23:48:59Z)
• Multi-Agents are Social Groups: Investigating Social Influence of Multiple Agents in Human-Agent Interactions [22.997945675889465]
  We investigate whether a group of AI agents can create social pressure on users to agree with them.<n>We found that conversing with multiple agents increased the social pressure felt by participants.<n>Our study shows the potential advantages of multi-agent systems over single-agent platforms in causing opinion change.
  arXiv  Detail & Related papers  (2024-11-07T10:00:46Z)
• Advancing Social Intelligence in AI Agents: Technical Challenges and Open Questions [67.60397632819202]
  Building socially-intelligent AI agents (Social-AI) is a multidisciplinary, multimodal research goal. We identify a set of underlying technical challenges and open questions for researchers across computing communities to advance Social-AI.
  arXiv  Detail & Related papers  (2024-04-17T02:57:42Z)
• Socially Pertinent Robots in Gerontological Healthcare [81.67026771075037]
  This paper is an attempt to partially answer the question, via two waves of experiments with patients and companions in a day-care gerontological facility in Paris with a full-sized humanoid robot endowed with social and conversational interaction capabilities.<n>Overall, the users are receptive to this technology, especially when the robot perception and action skills are robust to environmental clutter and flexible to handle a plethora of different interactions.
  arXiv  Detail & Related papers  (2024-04-11T08:43:37Z)
• SocialBench: Sociality Evaluation of Role-Playing Conversational Agents [85.6641890712617]
  Large language models (LLMs) have advanced the development of various AI conversational agents. SocialBench is the first benchmark designed to evaluate the sociality of role-playing conversational agents at both individual and group levels. We find that agents excelling in individual level does not imply their proficiency in group level.
  arXiv  Detail & Related papers  (2024-03-20T15:38:36Z)
• AI for social science and social science of AI: A Survey [47.5235291525383]
  Recent advancements in artificial intelligence have sparked a rethinking of artificial general intelligence possibilities. The increasing human-like capabilities of AI are also attracting attention in social science research.
  arXiv  Detail & Related papers  (2024-01-22T10:57:09Z)
• SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents [107.4138224020773]
  We present SOTOPIA, an open-ended environment to simulate complex social interactions between artificial agents and humans. In our environment, agents role-play and interact under a wide variety of scenarios; they coordinate, collaborate, exchange, and compete with each other to achieve complex social goals. We find that GPT-4 achieves a significantly lower goal completion rate than humans and struggles to exhibit social commonsense reasoning and strategic communication skills.
  arXiv  Detail & Related papers  (2023-10-18T02:27:01Z)
• PHASE: PHysically-grounded Abstract Social Events for Machine Social Perception [50.551003004553806]
  We create a dataset of physically-grounded abstract social events, PHASE, that resemble a wide range of real-life social interactions. Phase is validated with human experiments demonstrating that humans perceive rich interactions in the social events. As a baseline model, we introduce a Bayesian inverse planning approach, SIMPLE, which outperforms state-of-the-art feed-forward neural networks.
  arXiv  Detail & Related papers  (2021-03-02T18:44:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.