# Population Physics, Population Problems: Safety and Emergence in LLM Societies

arXiv: https://arxiv.org/abs/2609.33871 · HTML: https://mlsanity.com/paper/2609.33871/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 30 references that are in the map.
- First posted on arXiv 27 Sep 2026.

## Builds on (most cited first, 18 of 18)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https://mlsanity.com/paper/2308.10848/) (2023)
- [Are Emergent Abilities of Large Language Models a Mirage?](https://mlsanity.com/paper/2304.15004/) (2023)
- [RewardBench: Evaluating Reward Models for Language Modeling](https://mlsanity.com/paper/2403.13787/) (2024)
- [AI Control: Improving Safety Despite Intentional Subversion](https://mlsanity.com/paper/2312.06942/) (2023)
- [Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents](https://mlsanity.com/paper/2404.16698/) (2024)
- [Secret Collusion among AI Agents: Multi-Agent Deception via Steganography](https://mlsanity.com/paper/2402.07510/) (2024)
- [Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation](https://mlsanity.com/paper/2309.17234/) (2023)
- [Epidemic processes in complex networks](https://mlsanity.com/paper/1408.2701/) (2014)
- [Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM Agents](https://mlsanity.com/paper/2402.12327/) (2024)
- [When Autonomy Goes Rogue: Preparing for Risks of Multi-Agent Collusion in Social Systems](https://mlsanity.com/paper/2507.14660/) (2025)
- [Large Language Models and Emergence: A Complex Systems Perspective](https://mlsanity.com/paper/2506.11135/) (2025)
- [The Subtle Art of Defection: Understanding Uncooperative Behaviors in LLM based Multi-Agent Systems](https://mlsanity.com/paper/2511.15862/) (2025)
- [What Do AI Agents Talk About? Discourse and Architectural Constraints in the First AI-Only Social Network](https://mlsanity.com/paper/2603.07880/) (2026)
- [If LLMs Have Human-Like Attributes, Then So Does Age of Empires II](https://mlsanity.com/paper/2605.31514/) (2026)
- [Form Without Function: Agent Social Behavior in the Moltbook Network](https://mlsanity.com/paper/2604.13052/) (2026)

## Abstract (arXiv)

The collective behaviour of large language model (LLM) societies is not the sum of their individual outputs. It yields statistically distinct, sometimes-unpredictable phenomena, for which the tools we use to study single agents may not scale. Due to recent incidents involving autonomous agentic systems, however, understanding these systems is paramount. For that we introduce a framework for measuring self-organisation in LLM social systems and apply it to three such systems: a Schelling grid, a social network (Moltbook), and a Twitter-like misinformation simulation ('Rogue'). All three exhibit statistically significant self-organisation. Moreover, their relaxation dynamics vary with the environmental information available to the agents, with open-ended systems (Moltbook, Rogue) exhibiting sharp, phase-transition-like dynamics. Further results show that population-level pathologies can emerge even when the LLMs are safety-tuned or monitored, being primarily driven by the coordinated activity of a population subset. We also show when self-organisation does textitnot emerge under two additional scenarios (a commons dilemma, GovSim, and a LLM-as-a-judge deliberation scheme, ChatEval). We argue that measuring signatures of this kind offers a lightweight, agent-agnostic diagnostic layer for detecting coordinated collective behaviour in deployed multi-agent systems without relying on natural language or model versioning.