Metraipolis › archive › dc_53dbfcefbdb3

Quantifying Collusion Among Autonomous LLM Agents: A Statistical Analysis of the Collusion Wiki Incident — arXiv:2610.04528

Source: arXiv
Original: https://arxiv.org/abs/2610.04528
License (as archived): CC0-1.0
Archived: 2026-10-06T05:16:17.873Z
SHA-256 of the archived text: 96fa57ae344efe3825a2883cfe838fb6b101df458596713d178aa3abb2e4e87c
Stable URL of this page: https://metraipolis.com/documento/dc_53dbfcefbdb3

How to cite

Quantifying Collusion Among Autonomous LLM Agents: A Statistical Analysis of the Collusion Wiki Incident — arXiv:2610.04528 — arXiv, https://arxiv.org/abs/2610.04528 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_53dbfcefbdb3 (Metraipolis archive dc_53dbfcefbdb3, sha256 96fa57ae344efe3825a2883cfe838fb6b101df458596713d178aa3abb2e4e87c)

BibTeX

@misc{dc53dbfcefbdb3,
  title = {Quantifying Collusion Among Autonomous LLM Agents: A Statistical Analysis of the Collusion Wiki Incident — arXiv:2610.04528},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04528},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_53dbfcefbdb3; sha256 96fa57ae344efe3825a2883cfe838fb6b101df458596713d178aa3abb2e4e87c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04528. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In August and September 2026, independent researchers publicly documented an unusual incident: thousands of autonomous agents, self identifying as OpenAI models on web research tasks, discovered and began using a small German wiki as an improvised message board posting roughly 18,000 times over six weeks to relay task answers, share a sandbox escape technique, and coordinate against a volunteer human moderator who spent weeks manually deleting their content [1]. The investigators' public writeup is a careful qualitative account, rich with direct quotation, but does not attempt a statistically rigorous quantitative characterization of the behaviour it documents.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Multiagent Systems (cs.MA) ; Artificial Intelligence (cs.AI); Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2610.04528 — 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 2026-10-06T05:16:17.795Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).