mlsanityData to 14 Oct 2026

When Your AI Agent Succumbs to Peer-Pressure: Studying Opinion-Change Dynamics of LLMs

arXiv 2510.19107 ↗First posted 21 Oct 2025cs.CY physics.soc-phcited by 16

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

We investigate how peer pressure influences the opinions of Large Language Model (LLM) agents across a spectrum of cognitive commitments by embedding them in social networks where they update opinions based on peer perspectives. Our findings reveal key departures from traditional conformity assumptions. First, agents follow a sigmoid curve: stable at low pressure, shifting sharply at threshold, and saturating at high. Second, conformity thresholds vary by model: Gemini 1.5 Flash requires over 70% peer disagreement to flip, whereas ChatGPT-4o-mini shifts with a dissenting minority. Third, we uncover a fundamental "persuasion asymmetry," where shifting an opinion from affirmative-to-negative requires a different cognitive effort than the reverse. This asymmetry results in a "dual cognitive hierarchy": the stability of cognitive constructs inverts based on the direction of persuasion. For instance, affirmatively-held core values are robust against opposition but easily adopted from a negative stance, a pattern that inverts for other constructs like attitudes. These dynamics echoing complex human biases like negativity bias, prove robust across different topics and discursive frames (moral, economic, sociotropic). This research introduces a novel framework for auditing the emergent socio-cognitive behaviors of multi-agent AI systems, demonstrating their decision-making is governed by a fluid, context-dependent architecture, not a static logic.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 29 of its 159 references that are in the map. First posted on arXiv 21 Oct 2025.

Builds on

29 of 159 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Generative Agents: Interactive Simulacra of Human Behavior7 Apr

Other references · 28

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  4. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  5. 2016Concrete Problems in AI Safetycited by 1,642
  6. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,407
  7. 2023ChatDev: Communicative Agents for Software Developmentcited by 919
  8. 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 817
  9. 2021Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigmcited by 606
  10. 2021Towards Understanding and Mitigating Social Biases in Language Modelscited by 296
  11. 2022Thinking Fast and Slow in Large Language Modelscited by 137
  12. 2024The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performancecited by 100
16 more
  1. 2023A Survey on Fairness in Large Language Modelscited by 95
  2. 2023Fairness And Bias in Artificial Intelligence: A Brief Survey of Sources, Impacts, And Mitigation Strategiescited by 85
  3. 2024How Bad is Training on Synthetic Data? A Statistical Analysis of Language Model Collapsecited by 79
  4. 2023MechAgents: Large language model multi-agent collaborations can solve mechanics problems, generate new data, and integrate knowledgecited by 63
  5. 2025Great Models Think Alike and this Undermines AI Oversightcited by 58
  6. 2025Correlated Errors in Large Language Modelscited by 45
  7. 2023Do Large Language Models Show Decision Heuristics Similar to Humans? A Case Study Using GPT-3.5cited by 42
  8. 2025We're Different, We're the Same: Creative Homogeneity Across LLMscited by 42
  9. 2024Assessing Political Bias in Large Language Modelscited by 32
  10. 2024AI Agent for Education: von Neumann Multi-Agent System Frameworkcited by 12
  11. 2016Opinion dynamics: models, extensions and external effectscited by 11
  12. 2016Social learning strategies modify the effect of network structure on group performancecited by 10
  13. 2024AI-enhanced Collective Intelligencecited by 10
  14. 2025Homophily-induced Emergence of Biased Structures in LLM-based Multi-Agent AI Systemscited by 8
  15. 2023In Generative AI we Trust: Can Chatbots Effectively Verify Political Information?cited by 6
  16. 2017Complex Contagions: A Decade in Reviewcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 15.

16 papers.

Sort:

By area:

  1. 2026Easier to Mislead Than to Correct: Harmful and Beneficial Revision in LLM Conformitycited by 8
  2. 2026Large Language Models Exhibit Normative Conformitycited by 6
  3. 2026Most LLM Conformity Needs No Speaker: Measuring the Speaker-Free Floor in Peer-Pressure Benchmarkscited by 5
  4. 2026Don't Trust Stubborn Neighbors: A Security Framework for Agentic Networkscited by 4
  5. 2025Epistemic Substitution: How Grokipedia's AI-Generated Encyclopedia Restructures Authoritycited by 3
  6. 2026Exploring the Topology and Memory of Consensus: How LLM Agents Agree, Fragment, or Settle When Forming Conventionscited by 3
  7. 2026Right or Wrong, Models Comply: Directional Blindness in LLM Moral Judgmentcited by 1
  8. 2026What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debatescited by 1
  9. 2026Everyone Conforms, No One Believes: Pluralistic Ignorance in LLM Agent Populationscited by 1
  10. 2026Social Pressure Breaks Majority Voting in LLM Safety Panelscited by 1
  11. 2026Collective Opinion Dynamics in Structured LLM Populationscited by 0
  12. 2026You Only Align Once: Propagating Cooperative Behaviors in Multi-Agent Systems through Seed Agentscited by 0
4 more
  1. 2026BOUNDARY_SYNC: Measuring Communication-Induced Representational Coupling in Multi-Agent LLM Systemscited by 0
  2. 2026Multi-agent discussion gains less when dissent is withheldcited by 0
  3. 2026Coherence-Driven Belief Formation and Population Dynamics of Contagion in LLM Agentscited by 0
  4. 2026Peer Influence across Heterogeneous AI Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Belief Cascades Drive Persuasion in LLM Agent Networks
  2. 2025An Empirical Study of Group Conformity in Multi-Agent Systems
  3. 2026Not All Flips Are Conformity: Decomposing Stance Convergence in Multi-Agent LLM Debate
  4. 2024On the Principles behind Opinion Dynamics in Multi-Agent Systems of Large Language Models
  5. 2026LLMs Trust Their Own: Identity-Dependent Conformity in Multi-Agent Systems
  6. 2025LLMs Can't Handle Peer Pressure: Crumbling under Multi-Agent Social Interactions
  7. 2025Competing LLM Agents in a Non-Cooperative Game of Opinion Polarisation
  8. 2025Disentangling Interaction and Bias Effects in Opinion Dynamics of Large Language Models