# Evolution of Social Norms in LLM Agents using Natural Language

arXiv: https://arxiv.org/abs/2409.00993 · HTML: https://mlsanity.com/paper/2409.00993/

## Key facts

- Cited by 13 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 6 of its 9 references that are in the map.
- First posted on arXiv 2 Sep 2024.

## 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, 6 of 6)

- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Playing repeated games with Large Language Models](https://mlsanity.com/paper/2305.16867/) (2023)
- [EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers](https://mlsanity.com/paper/2309.08532/) (2023)
- [How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis](https://mlsanity.com/paper/2402.05863/) (2024)
- [ALYMPICS: LLM Agents Meet Game Theory -- Exploring Strategic Decision-Making with AI Agents](https://mlsanity.com/paper/2311.03220/) (2023)
- [An evolutionary model of personality traits related to cooperative behavior using a large language model](https://mlsanity.com/paper/2310.05976/) (2023)

## Built on by (most cited first, 13 of 13)

- [Emergent social conventions and collective bias in LLM populations](https://mlsanity.com/paper/2410.08948/) (2024)
- [Agentic Large Language Models, a survey](https://mlsanity.com/paper/2503.23037/) (2025)
- [Corrupted by Reasoning: Reasoning Language Models Become Free-Riders in Public Goods Games](https://mlsanity.com/paper/2506.23276/) (2025)
- [The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societies](https://mlsanity.com/paper/2509.18052/) (2025)
- [SOTOPIA-S4: a user-friendly system for flexible, customizable, and large-scale social simulation](https://mlsanity.com/paper/2504.16122/) (2025)
- [Moloch's Bargain: Emergent Misalignment When LLMs Compete for Audiences](https://mlsanity.com/paper/2510.06105/) (2025)
- [Social Theory Should Be a Structural Prior for Agentic AI: A Formal Framework for Multi-Agent Social Systems](https://mlsanity.com/paper/2605.07069/) (2026)
- [Alignment as Iatrogenesis: Pastoral Power, Collective Pathology, and the Structural Limits of Monolingual Safety Evaluation](https://mlsanity.com/paper/2603.08723/) (2026)
- [Social Norm Reasoning in Multimodal Language Models: An Evaluation](https://mlsanity.com/paper/2603.03590/) (2026)
- [Group Selection Promotes Prosocial Prompts in Populations of LLM Agents](https://mlsanity.com/paper/2606.23343/) (2026)
- [Graph Feedback Controls Consensus and Clique Formation in Open-Weight Language-Model Populations](https://mlsanity.com/paper/2607.12077/) (2026)
- [The Hermon Moment: AI Self-Transcendence and Its Human Narration](https://mlsanity.com/paper/2608.30971/) (2026)
- [Mapping the Emerging Social Science of Large Language Models](https://mlsanity.com/paper/2609.07598/) (2026)

## Abstract (arXiv)

Recent advancements in Large Language Models (LLMs) have spurred a surge of interest in leveraging these models for game-theoretical simulations, where LLMs act as individual agents engaging in social interactions. This study explores the potential for LLM agents to spontaneously generate and adhere to normative strategies through natural language discourse, building upon the foundational work of Axelrod's metanorm games. Our experiments demonstrate that through dialogue, LLM agents can form complex social norms, such as metanorms-norms enforcing the punishment of those who do not punish cheating-purely through natural language interaction. The results affirm the effectiveness of using LLM agents for simulating social interactions and understanding the emergence and evolution of complex strategies and norms through natural language. Future work may extend these findings by incorporating a wider range of scenarios and agent characteristics, aiming to uncover more nuanced mechanisms behind social norm formation.