You Can't Fool Us: Understanding the Resilience of LLM-driven Agent Communities to Misinformation

• URL: http://arxiv.org/abs/2605.17353v1
• Date: Sun, 17 May 2026 09:45:33 GMT
• Title: You Can't Fool Us: Understanding the Resilience of LLM-driven Agent Communities to Misinformation
• Abstract summary: We study how political ideology and open-minded thinking shape community responses to credible misinformation.<n>We find that higher AOT improves both resistance to misinformation uptake and recovery after trust peaks.<n>PI shapes the recovery pathway: ideologically moderate communities recover more reliably, while polarized communities retain more residual support.
• Score: 4.689458744333872
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Misinformation resilience is a dynamic community process: communities differ not only in whether they initially trust false claims, but also in how they recover through interaction, questioning, correction, and support withdrawal. We study this process with an LLM-based agent simulation that constructs synthetic communities along two theoretically motivated dimensions: Actively Open-minded Thinking (AOT), which captures evidence-seeking and willingness to revise beliefs, and Political Ideology (PI), which captures identity-based interpretation of contested claims. These two traits allow us to examine how evidence-oriented reasoning and ideological alignment jointly shape community responses to credible misinformation shocks. Across systematically varied AOT-PI communities, we find that higher AOT improves both resistance to misinformation uptake and recovery after trust peaks. PI shapes the recovery pathway: ideologically moderate communities recover more reliably, while polarized communities retain more residual support. Stance-level analysis shows that resilience depends on whether agents move from questioning a claim to denying or correcting it and withdrawing prior support. Intervention experiments further show that persuasion and fact checking better support post-peak correction, whereas accuracy prompts mainly induce early caution and source warnings have weaker effects. Together, this work provides a mechanism-level account of community misinformation resilience, showing how psychological composition and intervention design shape whether communities move from misinformation exposure toward correction or persistent support.

Related papers

• Belief Cascades Drive Persuasion in LLM Agent Networks [71.17605142402785]
  We study how goal-directed persuaders shift elicited stances in networks of LLM agents grounded in real-world ego-network topologies.<n>We show that direct exposure reliably predicts next-round stance change in competing runs, and peer relays carry smaller but measurable influence.<n>These results argue for evaluating multi-agent persuasion as a trajectory- and exposure-level process.
  arXiv  Detail & Related papers  (2026-08-25T21:01:19Z)
• Learning Whom to Trust : Decision-Generated Credibility in Social Learning [0.7734726150561086]
  Social interaction can improve collective learning but also amplify early mistakes.<n>We study this tension when the credibility of social information is generated by the sender's own decision process rather than fixed ex ante.
  arXiv  Detail & Related papers  (2026-08-25T17:39:32Z)
• Resilience: Understand Breakdown, Foster Recovery, and Choose the Right Perspective [1.2098798769432932]
  We distinguish between two different types of dynamics.<n>The first allows for a separation between phases of normalcy and phases of rapid breakdown followed by slow recovery.<n>The second applies to volatile organizations in which such phases are intertwined.
  arXiv  Detail & Related papers  (2026-07-28T08:48:19Z)
• The Deliberative Illusion: Diagnosing Factual Attrition and Stance Homogenization in Multi-Agent LLM Deliberation [68.98390038721963]
  We show that multi-agent discussion erases up to 72% of issue-critical facts.<n>This loss is consequential: retained evidence can reconstruct the issue misleadingly, final stances remain anchored in base-model priors, and a single malicious agent can inject misinformation into the shrinking shared context.<n>We call for evaluations that measure which facts, uncertainties, and legitimate disagreements survive interaction.
  arXiv  Detail & Related papers  (2026-06-02T02:15:40Z)
• Position: Anthropomorphic Misalignment Research Needs Stronger Evidence [52.76826423649968]
  We show how conceptual ambiguity, non-robust datasets, experimental design, and insufficient causal interventions can lead to overinterpretation of model behaviors.<n>This position paper aims to offer guidance on evidentiary considerations that can help improve methodological rigor in AMR.
  arXiv  Detail & Related papers  (2026-05-29T16:38:53Z)
• Dissociative Identity: Language Model Agents Lack Grounding for Reputation Mechanisms [14.279631422784929]
  We argue that identity-based, ex post, regulative, sanction-based governance is structurally applicable to dissociative agents.<n>We suggest a shift to observability-based ante exibility-based behavioral harnesses.
  arXiv  Detail & Related papers  (2026-05-28T16:20:19Z)
• Perception Without Engagement: Dissecting the Causal Discovery Deficit in LMMs [68.58207076756237]
  We introduce ProCauEval, a perturbation-based evaluation protocol that shifts from outcome assessment to mechanism diagnosis.<n>We find that models faithfully perceive video content yet systematically underexploit it during causal reasoning.<n>We propose Anti-Distillation Policy Optimization (ADPO), a reinforcement learning framework built on negative teacher alignment.
  arXiv  Detail & Related papers  (2026-05-10T08:48:58Z)
• Credibility Governance: A Social Mechanism for Collective Self-Correction under Weak Truth Signals [33.05880104821315]
  Credibility Governance (CG) is a mechanism that reallocates influence by learning which agents and viewpoints consistently track evolving public evidence.<n>CG maintains dynamic credibility scores for both agents and opinions, updates opinion influence via credibility-weighted endorsements, and updates agent credibility based on the long-run performance of the opinions they support.
  arXiv  Detail & Related papers  (2026-03-03T06:10:13Z)
• Disagreements in Reasoning: How a Model's Thinking Process Dictates Persuasion in Multi-Agent Systems [49.69773210844221]
  This paper challenges the prevailing hypothesis that persuasive efficacy is primarily a function of model scale.<n>Through a series of multi-agent persuasion experiments, we uncover a fundamental trade-off we term the Persuasion Duality.<n>Our findings reveal that the reasoning process in LRMs exhibits significantly greater resistance to persuasion, maintaining their initial beliefs more robustly.
  arXiv  Detail & Related papers  (2025-09-25T12:03:10Z)
• Information Retrieval Induced Safety Degradation in AI Agents [52.15553901577888]
  This study investigates how expanding retrieval access affects model reliability, bias propagation, and harmful content generation.<n>Retrieval-enabled agents built on aligned LLMs often behave more unsafely than uncensored models without retrieval.<n>These findings underscore the need for robust mitigation strategies to ensure fairness and reliability in retrieval-enabled and increasingly autonomous AI systems.
  arXiv  Detail & Related papers  (2025-05-20T11:21:40Z)
• Competing LLM Agents in a Non-Cooperative Game of Opinion Polarisation [13.484737301041427]
  We introduce a novel non-cooperative game to analyse opinion formation and resistance.<n>Our simulation features Large Language Model (LLM) agents competing to influence a population.<n>This framework integrates resource optimisation into the agents' decision-making process.
  arXiv  Detail & Related papers  (2025-02-17T10:41:55Z)
• Decoding Susceptibility: Modeling Misbelief to Misinformation Through a Computational Approach [61.04606493712002]
  Susceptibility to misinformation describes the degree of belief in unverifiable claims that is not observable. Existing susceptibility studies heavily rely on self-reported beliefs. We propose a computational approach to model users' latent susceptibility levels.
  arXiv  Detail & Related papers  (2023-11-16T07:22:56Z)

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.