智能体
arxiv.org ·
群体物理学，群体问题：LLM 社会中的安全与涌现
arXiv 预印本提出一个测量 LLM 社会系统自组织程度的框架，并应用于 Schelling grid、社交网络 Moltbook 和类 Twitter 虚假信息模拟 Rogue 三个系统，三者均表现出统计显著的自组织，开放式系统的弛豫动力学呈类似相变的尖锐变化。结果显示，即使 LLM 经过安全微调或受到监控，群体层面的病态行为仍可能出现，且主要由子群体的协同活动驱动；在 commons dilemma（GovSim）和 LLM-as-a-judge 审议（ChatEval）两个场景中则未观察到自组织。作者主张此类特征可作为轻量、与具体 agent 无关的诊断层，用于检测已部署多智能体系统中的协同集体行为，而不依赖自然语言或模型版本。
AI推荐理由 arXiv 预印本，作者 Adrian de Wynter，摘要明确给出方法与实验对象：提出测量 LLM 社会系统自组织程度的框架，并在 Schelling grid、社交网络 Moltbook、类 Twitter 虚假信息模拟 Rogue 三个系统中观察到统计显著的自组织，且开放式系统呈现类似相变的弛豫动力学；同时报告即使模型经过安全微调或监控，群体层面仍可能出现病态行为，主要由子群体的协同活动驱动，并在 GovSim 与 ChatEval 两个场景中未出现自组织。新信息在于把群体物理式诊断层用于多智能体安全监测，且声称不依赖自然语言或模型版本。局限是仅为预印本、尚未经同行评审，摘要未给出量化指标与复现细节，'安全微调仍失效'的结论需看全文验证。
78
正文
Computer Science > Multiagent Systems
arXiv:2609.33871 (cs)
[Submitted on 27 Sep 2026]
Title:Population Physics, Population Problems: Safety and Emergence in LLM Societies
Authors:Adrian de Wynter
View a PDF of the paper titled Population Physics, Population Problems: Safety and Emergence in LLM Societies, by Adrian de Wynter
View PDF
Abstract: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 \textit{not} 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.
Subjects:
Multiagent Systems (cs.MA); Computation and Language (cs.CL)
Cite as:
arXiv:2609.33871 [cs.MA]
(or
arXiv:2609.33871v1 [cs.MA] for this version)
https://doi.org/10.48550/arXiv.2609.33871
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Adrian de Wynter [view email]
[v1]
Sun, 27 Sep 2026 19:48:06 UTC (752 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Population Physics, Population Problems: Safety and Emergence in LLM Societies, by Adrian de Wynter
View PDF
TeX Source
view license
Current browse context:
cs.MA
new
|
recent
| 2026-09
Change to browse by:
cs
cs.CL
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)