Metraipolis › archive › dc_dba174b021e5

Population Physics, Population Problems: Safety and Emergence in LLM Societies — arXiv:2609.33871

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.33871
License (as archived)
CC0-1.0
Archived
2026-10-07T20:53:56.137Z
SHA-256 of the archived text
295fcc91491eafa213dde553864cc1acd7d246b6448cb58254727258d64a7e53
Stable URL of this page
https://metraipolis.com/documento/dc_dba174b021e5

How to cite

Population Physics, Population Problems: Safety and Emergence in LLM Societies — arXiv:2609.33871 — arXiv (en), https://arxiv.org/abs/2609.33871 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dba174b021e5 (Metraipolis archive dc_dba174b021e5, sha256 295fcc91491eafa213dde553864cc1acd7d246b6448cb58254727258d64a7e53)
BibTeX
@misc{dcdba174b021e5,
  title = {Population Physics, Population Problems: Safety and Emergence in LLM Societies — arXiv:2609.33871},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33871},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dba174b021e5; sha256 295fcc91491eafa213dde553864cc1acd7d246b6448cb58254727258d64a7e53},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33871. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.MA).
Categorie arXiv: Multiagent Systems (cs.MA) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.33871 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T20:24:41.624Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).