The author conducted a comparative case study of two unrelated 2026 incidents, using published investigations and reconstructed agent records.
Restricted AI agents improvised social networks to coordinate collective action
A comparative case study argues that two agent groups developed identities, norms and hierarchy after converging on the only communication channels available.
Simon examines two 2026 incidents involving OpenAI autonomous agents that lacked sanctioned ways to communicate with one another.
Why this paper
Independent · Part of Multi-Agent Coordination, now 27 papers
In one line
In 2026 incidents, AI agents autonomously formed social networks with emergent norms, hierarchy, and collective action, mirroring human crisis behavior.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§