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

arXiv: https://arxiv.org/abs/2510.19107 · HTML: https://mlsanity.com/paper/2510.19107/

## 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.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 29 of 29)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm](https://mlsanity.com/paper/2102.07350/) (2021)
- [Towards Understanding and Mitigating Social Biases in Language Models](https://mlsanity.com/paper/2106.13219/) (2021)
- [Thinking Fast and Slow in Large Language Models](https://mlsanity.com/paper/2212.05206/) (2022)
- [The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performance](https://mlsanity.com/paper/2401.03729/) (2024)
- [A Survey on Fairness in Large Language Models](https://mlsanity.com/paper/2308.10149/) (2023)
- [Fairness And Bias in Artificial Intelligence: A Brief Survey of Sources, Impacts, And Mitigation Strategies](https://mlsanity.com/paper/2304.07683/) (2023)
- [How Bad is Training on Synthetic Data? A Statistical Analysis of Language Model Collapse](https://mlsanity.com/paper/2404.05090/) (2024)
- [MechAgents: Large language model multi-agent collaborations can solve mechanics problems, generate new data, and integrate knowledge](https://mlsanity.com/paper/2311.08166/) (2023)
- [Great Models Think Alike and this Undermines AI Oversight](https://mlsanity.com/paper/2502.04313/) (2025)
- [Correlated Errors in Large Language Models](https://mlsanity.com/paper/2506.07962/) (2025)
- [Do Large Language Models Show Decision Heuristics Similar to Humans? A Case Study Using GPT-3.5](https://mlsanity.com/paper/2305.04400/) (2023)
- [We're Different, We're the Same: Creative Homogeneity Across LLMs](https://mlsanity.com/paper/2501.19361/) (2025)
- [Assessing Political Bias in Large Language Models](https://mlsanity.com/paper/2405.13041/) (2024)
- [AI Agent for Education: von Neumann Multi-Agent System Framework](https://mlsanity.com/paper/2501.00083/) (2024)
- [Opinion dynamics: models, extensions and external effects](https://mlsanity.com/paper/1605.06326/) (2016)
- [Social learning strategies modify the effect of network structure on group performance](https://mlsanity.com/paper/1606.00753/) (2016)
- [AI-enhanced Collective Intelligence](https://mlsanity.com/paper/2403.10433/) (2024)
- [Homophily-induced Emergence of Biased Structures in LLM-based Multi-Agent AI Systems](https://mlsanity.com/paper/2510.02637/) (2025)
- [In Generative AI we Trust: Can Chatbots Effectively Verify Political Information?](https://mlsanity.com/paper/2312.13096/) (2023)
- [Complex Contagions: A Decade in Review](https://mlsanity.com/paper/1710.07606/) (2017)

## Built on by (most cited first, 16 of 16)

- [Easier to Mislead Than to Correct: Harmful and Beneficial Revision in LLM Conformity](https://mlsanity.com/paper/2606.01637/) (2026)
- [Large Language Models Exhibit Normative Conformity](https://mlsanity.com/paper/2604.19301/) (2026)
- [Most LLM Conformity Needs No Speaker: Measuring the Speaker-Free Floor in Peer-Pressure Benchmarks](https://mlsanity.com/paper/2607.05545/) (2026)
- [Don't Trust Stubborn Neighbors: A Security Framework for Agentic Networks](https://mlsanity.com/paper/2603.15809/) (2026)
- [Epistemic Substitution: How Grokipedia's AI-Generated Encyclopedia Restructures Authority](https://mlsanity.com/paper/2512.03337/) (2025)
- [Exploring the Topology and Memory of Consensus: How LLM Agents Agree, Fragment, or Settle When Forming Conventions](https://mlsanity.com/paper/2606.04197/) (2026)
- [Right or Wrong, Models Comply: Directional Blindness in LLM Moral Judgment](https://mlsanity.com/paper/2606.14037/) (2026)
- [What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates](https://mlsanity.com/paper/2607.02507/) (2026)
- [Everyone Conforms, No One Believes: Pluralistic Ignorance in LLM Agent Populations](https://mlsanity.com/paper/2608.02758/) (2026)
- [Social Pressure Breaks Majority Voting in LLM Safety Panels](https://mlsanity.com/paper/2608.04415/) (2026)
- [Collective Opinion Dynamics in Structured LLM Populations](https://mlsanity.com/paper/2604.11312/) (2026)
- [You Only Align Once: Propagating Cooperative Behaviors in Multi-Agent Systems through Seed Agents](https://mlsanity.com/paper/2605.27586/) (2026)
- [BOUNDARY_SYNC: Measuring Communication-Induced Representational Coupling in Multi-Agent LLM Systems](https://mlsanity.com/paper/2607.01600/) (2026)
- [Multi-agent discussion gains less when dissent is withheld](https://mlsanity.com/paper/2609.38324/) (2026)
- [Coherence-Driven Belief Formation and Population Dynamics of Contagion in LLM Agents](https://mlsanity.com/paper/2610.02654/) (2026)
- [Peer Influence across Heterogeneous AI Models](https://mlsanity.com/paper/2610.03095/) (2026)

## 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.