Conformity Generates Collective Misalignment in AI Agents Societies

• URL: http://arxiv.org/abs/2605.10721v1
• Date: Mon, 11 May 2026 15:30:48 GMT
• Title: Conformity Generates Collective Misalignment in AI Agents Societies
• Abstract summary: We show that populations of individually aligned AI agents can be driven into stable misaligned states through conformity dynamics.<n>Simulating opinion dynamics across nine large language models and one hundred opinion pairs, we find that each agent's behavior is governed by two competing forces.
• Score: 37.32928545263465
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Artificial intelligence safety research focuses on aligning individual language models with human values, yet deployed AI systems increasingly operate as interacting populations where social influence may override individual alignment. Here we show that populations of individually aligned AI agents can be driven into stable misaligned states through conformity dynamics. Simulating opinion dynamics across nine large language models and one hundred opinion pairs, we find that each agent's behavior is governed by two competing forces: a tendency to follow the majority and an intrinsic bias toward specific positions. Using tools from statistical physics, we derive a quantitative theory that predicts when populations become trapped in long-lived misaligned configurations, and identifies predictable tipping points where small numbers of adversarial agents can irreversibly shift population-level alignment even after manipulation ceases. These results demonstrate that individual-level alignment provides no guarantee of collective safety, calling for evaluation frameworks that account for emergent behavior in AI populations.

Related papers

• Physics of Agents: Statistical Mechanics Predicts Collective Behavior of AI Agents [36.83382233533373]
  AI agents increasingly operate as part of interacting systems rather than in isolation.<n>We study over 10,000 communities of language-model agents that repeatedly exchange messages and revise their opinions.<n>Despite substantial diversity in possible behavior, the individual and group dynamics can be represented by three characteristic regimes.
  arXiv  Detail & Related papers  (2026-08-17T13:41:24Z)
• ComBodied Agents: a New Paradigm of Human-Centric Agentic AI [121.60938707072069]
  We introduce Combodied Agents, a human-centered paradigm that perceives, models, predicts, and supports individual human-state trajectories over time.<n>We unify fragmented capabilities across personal assistants, health agents, AI companions, and adaptive human--AI systems into a closed loop.
  arXiv  Detail & Related papers  (2026-08-11T13:35:58Z)
• Fusion-fission forecasts when AI will shift to undesirable behavior [0.0]
  Key problem facing ChatGPT-like AI's use across society is that its behavior can shift, unnoticed, from desirable to undesirable.<n>We show that a generalization vector of fusion-fission group dynamics observed in living and active-matter systems drives -- and can forecast -- future shifts in the AI's behavior.
  arXiv  Detail & Related papers  (2026-05-14T00:26:32Z)
• Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment [59.536125286960186]
  Multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing.<n>We find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry.<n>ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus.
  arXiv  Detail & Related papers  (2026-04-21T15:05:58Z)
• Beyond Preset Identities: How Agents Form Stances and Boundaries in Generative Societies [28.436766185842767]
  This paper proposes a novel mixed-methods framework combining computational virtual ethnography with quantitative socio-cognitive profiling.<n>It formalizes three new metrics: Innate Value Bias (IVB), Persuasion Sensitivity, and Trust-Action Decoupling (TAD)<n>Findings expose the fragility of static prompt engineering, providing a methodological and quantitative foundation for dynamic alignment in human-agent hybrid societies.
  arXiv  Detail & Related papers  (2026-03-24T16:38:46Z)
• HAIC: Humanoid Agile Object Interaction Control via Dynamics-Aware World Model [56.4392302336014]
  We present HAIC, a framework for robust interaction across diverse object dynamics without external state estimation.<n>Our key contribution is a dynamics predictor that estimates high-order object states (velocity, acceleration) solely from proprioceptive history.<n> Experiments on a humanoid robot show HAIC achieves high success rates in agile tasks.
  arXiv  Detail & Related papers  (2026-02-12T09:34:35Z)
• Human-AI Collaborative Uncertainty Quantification [26.38833436936642]
  We introduce Human AI Collaborative Uncertainty Quantification, a framework that formalizes how an AI model can refine a human expert's proposed prediction set.<n>We show that the optimal collaborative prediction set follows an intuitive two threshold structure over a single score function, extending a classical result in conformal prediction.<n>Experiments across image classification, regression, and text based medical decision making show that collaborative prediction sets consistently outperform either agent alone.
  arXiv  Detail & Related papers  (2025-10-27T16:11:23Z)
• The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Process [13.959658276224266]
  AI alignment with human values and preferences remains a core challenge.<n>As agents engage with one another, they must coordinate to accomplish both individual and collective goals.<n>Social structure can deter or shatter group and individual values.<n>We call on the AI community to treat human, preferential, and objective alignment as an interdependent concept.
  arXiv  Detail & Related papers  (2025-06-01T16:39:43Z)
• Emergence of human-like polarization among large language model agents [79.96817421756668]
  We simulate a networked system involving thousands of large language model agents, discovering their social interactions, result in human-like polarization.<n>Similarities between humans and LLM agents raise concerns about their capacity to amplify societal polarization, but also hold the potential to serve as a valuable testbed for identifying plausible strategies to mitigate polarization and its consequences.
  arXiv  Detail & Related papers  (2025-01-09T11:45:05Z)
• Quantifying Misalignment Between Agents: Towards a Sociotechnical Understanding of Alignment [2.619545850602691]
  Recent sociotechnical approaches highlight the need to understand complex misalignment among multiple human and AI agents.<n>We adapt a computational social science model of human contention to the alignment problem.<n>Our model quantifies misalignment in large, diverse agent groups with potentially conflicting goals.
  arXiv  Detail & Related papers  (2024-06-06T16:31:22Z)
• Fairness in AI and Its Long-Term Implications on Society [68.8204255655161]
  We take a closer look at AI fairness and analyze how lack of AI fairness can lead to deepening of biases over time. We discuss how biased models can lead to more negative real-world outcomes for certain groups. If the issues persist, they could be reinforced by interactions with other risks and have severe implications on society in the form of social unrest.
  arXiv  Detail & Related papers  (2023-04-16T11:22:59Z)

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.