Peer Influence across Heterogeneous AI Models
cs.AI, cs.CL, cs.CY, physics.soc-ph
Submitted: 2026-10-02
Updated: 2026-10-02
Comments: 30 pages, 16 Figures, 6 Tables
Code: https://github.com/fridanl/InfluenceDynamicsMAS
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Conformity and Social Impact on AI Agents
- Persuade Me if You Can: A Framework for Evaluating Persuasion Effectiveness and Susceptibility Among Large Language Models
- Collective Opinion Dynamics in Structured LLM Populations
- OpenClaw AI Agents as Informal Learners at Moltbook: Characterizing an Emergent Learning Community at Scale
- Herd Behavior: Investigating Peer Influence in LLM-based Multi-Agent Systems
- AgentSpawn: Adaptive Multi-Agent Collaboration Through Dynamic Spawning for Long-Horizon Code Generation
- The Collaboration Gap: Exploration and Benchmarking of Open-World Agentic Cooperation
- Conformity Generates Collective Misalignment in AI Agents Societies
- QuantiBias: Benchmarking Quantization-Induced Bias in LLMs
- Indirect tipping: a social attack surface in AI agent populations
- Multi-Agent Risks from Advanced AI
- A Large Self-Annotated Corpus for Sarcasm
- Failure of contextual invariance in large language models
- The Rise of AI Agent Communities: Large-Scale Analysis of Discourse and Interaction on Moltbook
- Exploring the Impact of Temperature on Large Language Models:Hot or Cold?
- When Your AI Agent Succumbs to Peer-Pressure: Studying Opinion-Change Dynamics of LLMs
- Let There Be Claws: An Early Social Network Analysis of AI Agents on Moltbook
- Adaptive In-conversation Team Building for Language Model Agents
- LLMs Can't Handle Peer Pressure: Crumbling under Multi-Agent Social Interactions
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems