mlsanityData to 7 Oct 2026

Emergence of Social Norms in Generative Agent Societies: Principles and Architecture

arXiv 2403.08251 ↗First posted 13 Mar 2024cs.MA cs.AI cs.CYcited by 41

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

Abstract (arXiv)

Social norms play a crucial role in guiding agents towards understanding and adhering to standards of behavior, thus reducing social conflicts within multi-agent systems (MASs). However, current LLM-based (or generative) MASs lack the capability to be normative. In this paper, we propose a novel architecture, named CRSEC, to empower the emergence of social norms within generative MASs. Our architecture consists of four modules: Creation & Representation, Spreading, Evaluation, and Compliance. This addresses several important aspects of the emergent processes all in one: (i) where social norms come from, (ii) how they are formally represented, (iii) how they spread through agents' communications and observations, (iv) how they are examined with a sanity check and synthesized in the long term, and (v) how they are incorporated into agents' planning and actions. Our experiments deployed in the Smallville sandbox game environment demonstrate the capability of our architecture to establish social norms and reduce social conflicts within generative MASs. The positive outcomes of our human evaluation, conducted with 30 evaluators, further affirm the effectiveness of our approach. Our project can be accessed via the following link: https://github.com/sxswz213/CRSEC.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 15 of its 64 references that are in the map. First posted on arXiv 13 Mar 2024.

Builds on

15 of 64 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Agent Alignment in Evolving Social Norms9 Jan
  2. 2023Generative Agents: Interactive Simulacra of Human Behavior7 Apr

Other references · 13

  1. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  2. 2021Persistent Anti-Muslim Bias in Large Language Modelscited by 376
  3. 2023Role-Play with Large Language Modelscited by 290
  4. 2021All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Textcited by 287
  5. 2021Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Docited by 178
  6. 2023SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Taskscited by 166
  7. 2023Training Socially Aligned Language Models on Simulated Social Interactionscited by 77
  8. 2023Knowledge of cultural moral norms in large language modelscited by 51
  9. 2023LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordinationcited by 48
  10. 2022Do Multilingual Language Models Capture Differing Moral Norms?cited by 15
  11. 2023A Data Fusion Framework for Multi-Domain Morality Learningcited by 14
  12. 2024Learning and Sustaining Shared Normative Systems via Bayesian Rule Induction in Markov Gamescited by 11
1 more
  1. 2024Norm Enforcement with a Soft Touch: Faster Emergence, Happier Agentscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 13; 2026: 26.

41 papers.

Sort:

By area:

  1. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  2. 2024A Survey on Large Language Model-Based Social Agents in Game-Theoretic Scenarioscited by 23
  3. 2025Nuclear Deployed: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agentscited by 23
  4. 2025Towards a Design Guideline for RPA Evaluation: A Survey of Large Language Model-Based Role-Playing Agentscited by 22
  5. 2025Can A Society of Generative Agents Simulate Human Behavior and Inform Public Health Policy? A Case Study on Vaccine Hesitancycited by 15
  6. 2026A Survey on LLM-based Conversational User Simulationcited by 14
  7. 2025The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societiescited by 12
  8. 2025LLM-Based Social Simulations Require a Boundarycited by 11
  9. 2026Agentic World Modeling: Foundations, Capabilities, Laws, and Beyondcited by 10
  10. 2025The Role of Social Learning and Collective Norm Formation in Fostering Cooperation in LLM Multi-Agent Systemscited by 8
  11. 2024Harnessing the power of LLMs for normative reasoning in MASscited by 7
  12. 2025Evolution of Cooperation in LLM-Agent Societies: A Preliminary Study Using Different Punishment Strategiescited by 6
29 more
  1. 2025Reputation as a Solution to Cooperation Collapse in LLM-based MASscited by 6
  2. 2026Generative AI collective behavior needs an interactionist paradigmcited by 6
  3. 2026Stop Drawing Scientific Claims from LLM Social Simulations Without Robustness Auditscited by 6
  4. 2025How Social is It? A Benchmark for LLMs' Capabilities in Multi-user Multi-turn Social Agent Taskscited by 3
  5. 2025Ev-Trust: An Evolutionarily Stable Trust Mechanism for Decentralized LLM-Based Multi-Agent Service Economiescited by 3
  6. 2026When AI Agents Teach Each Other: Discourse Patterns Resembling Peer Learning in the Moltbook Communitycited by 3
  7. 2026Emergence World: A Platform for Evaluating Long-Horizon Multi-Agent Autonomycited by 3
  8. 2026ScaleSim: Serving Large-Scale Multi-Agent Simulation with Invocation Distance-Based Memory Managementcited by 2
  9. 2025LLM-based Multi-Agent System for Simulating Strategic and Goal-Oriented Data Marketplacescited by 1
  10. 2026Social Norm Reasoning in Multimodal Language Models: An Evaluationcited by 1
  11. 2026The Moltbook Files: A Harmless Slopocalypse or Humanity's Last Experimentcited by 1
  12. 2026Behavior is Not Enough: A Mechanism-Based Evaluation of Social Norm Emergence in LLM Societiescited by 1
  13. 2025Adaptive Accountability in Networked MAS: Tracing and Mitigating Emergent Norms at Scalecited by 0
  14. 2026Bounded Normative Equivalence in Human-AI Cooperation: Group Behaviour, Not Partner Labels, Predicts Cooperation under Anonymous Aggregate Feedbackcited by 0
  15. 2026LLM-Augmented Digital Twin for Policy Evaluation in Short-Video Platformscited by 0
  16. 2026How do Role Models Shape Collective Morality? Exemplar-Driven Moral Learning in Multi-Agent Simulationcited by 0
  17. 2026CAMO: An Agentic Framework for Automated Causal Discovery from Micro Behaviors to Macro Emergence in LLM Agent Simulationscited by 0
  18. 2026Mechanism Plausibility in Generative Agent-Based Modelingcited by 0
  19. 2026PAVE: A Cognitive Architecture for Legitimate Violation in Generative Agent Societiescited by 0
  20. 2026You Only Align Once: Propagating Cooperative Behaviors in Multi-Agent Systems through Seed Agentscited by 0
  21. 2026Emergent Relational Order in LLM Agent Societies: From Collective Affect to Authority Stratificationcited by 0
  22. 2026Graph Feedback Controls Consensus and Clique Formation in Open-Weight Language-Model Populationscited by 0
  23. 2026Eco3S: Complex Socio-Economic System Simulation via Agent-Based Modelscited by 0
  24. 2026LLMs struggle to simulate human belief updates in controlled environmentscited by 0
  25. 2026Relational Priors as Convergence Pressure in LLM-Based Multi-Agent Systemscited by 0
  26. 2026Grounded Normative Rule Generation with Structured Searchcited by 0
  27. 2026Benchmarking large language model agent societies against human behavioural distributionscited by 0
  28. 2026Tipping Points in LLM-Based Multi-Agent Systems: Stance on Climate Change Actioncited by 0
  29. 2026Who Owns That? Evaluating Ownership Intuitions in Large Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Normative Modules: A Generative Agent Architecture for Learning Norms that Supports Multi-Agent Cooperation
  2. 2026Reading the Room: Foundations, Design, and Challenges of Normative Competence in LLMs
  3. 2024Evolution of Social Norms in LLM Agents using Natural Language
  4. 2024Can Agents Spontaneously Form a Society? Introducing a Novel Architecture for Generative Multi-Agents to Elicit Social Emergence
  5. 2026Socially Grounded Agentic AI: Coordinating Plural Perspectives through Social Theory
  6. 2024Norm Violation Detection in Multi-Agent Systems using Large Language Models: A Pilot Study
  7. 2026Social Theory Should Be a Structural Prior for Agentic AI: A Formal Framework for Multi-Agent Social Systems
  8. 2025AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society