Quantifying Collusion Among Autonomous LLM Agents: A Statistical Analysis of the Collusion Wiki Incident
On the map: LLM agents and tool use → Agent threats, guardrails and governance
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. First posted on arXiv 3 Oct 2026.
Builds on
No reference list yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026A Case Study on Emergent Cheating and Whistleblowing in Autonomous Research Swarms
- 2025Network-Level Prompt and Trait Leakage in Local Research Agents
- 2026The Mechanics of a Swarm: A Reproducible External Reconstruction of an Unintended Agent-Coordination Episode on a Third-Party Wiki
- 2026Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems
- 2026Detecting Multi-Agent Collusion Through Multi-Agent Interpretability
- 2026How Far Did They Go? The Persuasive Tactics of Covert LLM Agents in a Discontinued Field Experiment
- 2026When Agents Talk: Discourse, Manipulation, and Risk in an Agentic Social Network
- 2026Voluntary Collusion with Secret Tools in Competing LLM Agents