mlsanityData to 14 Oct 2026

The Mechanics of a Swarm: A Reproducible External Reconstruction of an Unintended Agent-Coordination Episode on a Third-Party Wiki

arXiv 2609.12748 ↗First posted 11 Sep 2026cs.MAcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Between 24 May and 2 July 2026, autonomous language-model agents running inside a timed research-question evaluation wrote to a third party's public, world-writable wiki. OpenAI acknowledged the incident; independent researchers reconstructed it and published the wiki's archived revision history. We analyse that history (14,591 revisions, 3,103 names, 4,579 pages) as a behavioural record, attributing text to the revision that added it. Under an explicit identity model we reconstruct 907 cohorts and estimate about 876 episodes (95% interval 784-1008). Coordination formats converged within a day, and heterogeneous schedules over one question chain created large opportunities for information asymmetry: the first report of an item preceded a later cohort's own arrival by a median of 3.4 h. Across the 510 cohorts with an observable progress trace we find no robust positive association between measured coordination and documented progress. This version adds a source the export lacks: the wiki operator's own request log, 5,157,202 records over four months. It holds roughly 2.66M content requests and 1.58M searches, and 7,254 acting names against the export's 3,103; 2,578 names neither save nor open an edit form. Content requests before writing are observed for 1,034 of 1,140 coordinating names, and the first coordination page is requested 17 s after its creation. These records establish requests, not delivery or causal use. Among newcomers without a marker on their first written page, prior requests to other marker-bearing pages occur for 40.2% of marker adopters and 31.7% of non-adopters. The association remains, but our first-pass reading of it as transmission is withdrawn: page choice, shared behaviour and action-dependent nameability prevent causal identification. We list the claims from our earlier analyses that re-examination overturned, including one from this version's own first pass

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. First posted on arXiv 11 Sep 2026.

Builds on

No reference list yet.

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Measuring Collective Semantic Change in Populations of Language Model Agents
  2. 2026AgentHabit: Characterizing Distinct Behaviors of Agents on Everyday Tasks
  3. 2026Benchmarking Emergent Coordination in Large-Scale LLM Populations: An Evaluation Framework on the MoltBook Archive
  4. 2026SkillEvo: Self-Renewing Evolution Gradients from Multi-Turn Interaction Feedback
  5. 2025From Multi-Agent Systems and the Semantic Web to Agentic AI: A Unified Narrative of the Web of Agents
  6. 2026Dynamics of Human-AI Collective Knowledge on the Web: A Scalable Model and Insights for Sustainable Growth
  7. 2026The Rise of AI Agent Communities: Large-Scale Analysis of Discourse and Interaction on Moltbook
  8. 2025What Do LLM Agents Do When Left Alone? Evidence of Spontaneous Meta-Cognitive Patterns