mlsanityData to 14 Oct 2026

Herd Behavior: Investigating Peer Influence in LLM-based Multi-Agent Systems

arXiv 2505.21588 ↗First posted 27 May 2025cs.MA cs.AIcited by 15

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

Abstract (arXiv)

Recent advancements in Large Language Models (LLMs) have enabled the emergence of multi-agent systems where LLMs interact, collaborate, and make decisions in shared environments. While individual model behavior has been extensively studied, the dynamics of peer influence in such systems remain underexplored. In this paper, we investigate herd behavior, the tendency of agents to align their outputs with those of their peers, within LLM-based multi-agent interactions. We present a series of controlled experiments that reveal how herd behaviors are shaped by multiple factors. First, we show that the gap between self-confidence and perceived confidence in peers significantly impacts an agent's likelihood to conform. Second, we find that the format in which peer information is presented plays a critical role in modulating the strength of herd behavior. Finally, we demonstrate that the degree of herd behavior can be systematically controlled, and that appropriately calibrated herd tendencies can enhance collaborative outcomes. These findings offer new insights into the social dynamics of LLM-based systems and open pathways for designing more effective and adaptive multi-agent collaboration frameworks.

Key facts. Cited by 15 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 21 of its 34 references that are in the map. First posted on arXiv 27 May 2025.

Builds on

21 of 34 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025The Hidden Strength of Disagreement: Unraveling the Consensus-Diversity Tradeoff in Adaptive Multi-Agent Systems23 Feb
  2. 2024GroupDebate: Enhancing the Efficiency of Multi-Agent Debate Using Group Discussion21 Sep
  3. 2024Exploring Prosocial Irrationality for LLM Agents: A Social Cognition View23 May
  4. 2023Generative Agents: Interactive Simulacra of Human Behavior7 Apr

Other references · 17

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  3. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  4. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,848
  5. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  6. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  7. 2023Whose Opinions Do Language Models Reflect?cited by 773
  8. 2023Towards Measuring the Representation of Subjective Global Opinions in Language Modelscited by 437
  9. 2023Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Gamecited by 152
  10. 2018Quantifying Uncertainties in Natural Language Processing Taskscited by 79
  11. 2023Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experimentcited by 77
  12. 2025Do as We Do, Not as You Think: the Conformity of Large Language Modelscited by 53
5 more
  1. 2021Structural Persistence in Language Models: Priming as a Window into Abstract Language Representationscited by 44
  2. 2024Do Language Models Exhibit Human-like Structural Priming Effects?cited by 21
  3. 2024AI Can Be Cognitively Biased: An Exploratory Study on Threshold Priming in LLM-Based Batch Relevance Assessmentcited by 20
  4. 2013Social Influence and the Collective Dynamics of Opinion Formationcited by 16
  5. 2017When confidence and competence collide: Effects on online decision-making discussionscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 12.

15 papers.

Sort:

By area:

  1. 2025Free-MAD: Consensus-Free Multi-Agent Debatecited by 29
  2. 2025LLMs Can't Handle Peer Pressure: Crumbling under Multi-Agent Social Interactionscited by 16
  3. 2025The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societiescited by 14
  4. 2026FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systemscited by 7
  5. 2026Not All Flips Are Conformity: Decomposing Stance Convergence in Multi-Agent LLM Debatecited by 7
  6. 2026Epistemic Context Learning: Building Trust the Right Way in LLM-Based Multi-Agent Systemscited by 6
  7. 2026Large Language Models Exhibit Normative Conformitycited by 6
  8. 2026When Planning Fails Despite Correct Execution: On Epistemic Calibration for LLM-Based Multi-Agent Systemscited by 3
  9. 2026Agentic Microphysics: A Manifesto for Generative AI Safetycited by 2
  10. 2026Social Networks of LLM Agentscited by 2
  11. 2026One Axis, No Brake: Self-Knowledge Limits the Filtering of Harmful Peer Conformity in LLMscited by 1
  12. 2026BOUNDARY_SYNC: Measuring Communication-Induced Representational Coupling in Multi-Agent LLM Systemscited by 0
3 more
  1. 2026When Upstream Messages Override Correct Answers: A Controlled Study of Multi-Agent LLM Collaborationcited by 0
  2. 2026When Order Matters: First-Speaker Bias and Mitigation through Personality in Sequential Multi-Agent Debatecited by 0
  3. 2026Workerville: Towards an Organizational Behavior Account of Agent Safetycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Group size effects and collective misalignment in LLM multi-agent systems
  2. 2024Network Formation and Dynamics Among Multi-LLMs
  3. 2025Learning to Make Friends: Coaching LLM Agents toward Emergent Social Ties
  4. 2026Collective cooperation without individual fidelity in LLM agents
  5. 2026Conformity Dynamics in LLM Multi-Agent Systems: The Roles of Topology and Self-Social Weighting
  6. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View
  7. 2026Talk, Judge, Cooperate: Gossip-Driven Indirect Reciprocity in Self-Interested LLM Agents
  8. 2024Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM Agents