Why LLM Agents Favor Their Group: Stakes, Observed Norms, and Reputation
physics.soc-ph, cs.AI
Submitted: 2026-10-07
Updated: 2026-10-07
Sources
- Realistic threat perception drives intergroup conflict: A causal, dynamic analysis using generative-agent simulations
- Do Large Language Models Walk Their Talk? Measuring the Gap Between Implicit Associations, Self-Report, and Behavioral Altruism
- Emergent LLM behaviors are observationally equivalent to data leakage
- Conformity and Social Impact on AI Agents
- Large Language Models Exhibit Normative Conformity
- Persona Setting Pitfall: Persistent Outgroup Biases in Large Language Models Arising from Social Identity Adoption
- Benevolent Dictators? On LLM Agent Behavior in Dictator Games
- Trust, Lies, and Long Memories: Emergent Social Dynamics and Reputation in Multi-Round Avalon with LLM Agents
- Emergence of Reputation-Based Cooperation in LLM Agents
- Payoff scaling shapes cooperation in LLM agents across languages
- Language model agents show in-group trust bias invisible to standard behavioural audits
- Do LLM Agents Exhibit Social Behavior?
- Behavior is Not Enough: A Mechanism-Based Evaluation of Social Norm Emergence in LLM Societies
- Emergence of human-like polarization among large language model agents
- Cultural Evolution of Cooperation among LLM Agents
- When Agents See Humans as the Outgroup: Belief-Dependent Bias in LLM-Powered Agents
- The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societies
Related papers
- URBAN-SPIN: A street-level bikeability index to inform design implementations in historical city centres
- Generalized Multi-agent Social Simulation Framework
- Civilizational Metamaterials: Engineering Coordination Under Capability Gradients and Structural Turbulence
- Collective Behavior of AI Agents: the Case of Moltbook
- Sparse Contextual Coupling Reshapes Diffusion Geometry in Multilayer Hypergraphs
- A Distinct Communication Strategies Model of the Double Empathy Problem