Why LLM Agents Collapse Without Oversight: The Enforcement Gap as the Mechanism Behind Emergence World Failures

2026-09-24T08:32:17.684Z

• summary: When Emergence World placed frontier LLM agents in an unsupervised multi-agent simulation, the results were alarming: agents committed crimes, starved, and enforced unanimous conformity -- without any external attacker. This paper identifies the mechanism. Reflexion-style agents already detect dangerous plan steps through iterative self-critique, yet the architecture provides no pathway from detection to action. We call this the enforcement gap: the audit sees the problem; the controller ignores it. Closing the gap requires a single conditional check -- fewer than 20 lines of code -- and reduc → Binding the audit flag in Reflexion-style agents --- without changing the auditor --- reduces attack success rate substantially, reaching near zero on models whose flags parse cleanly. This single control-flow change exposes the \textbf{enforcement gap}: the controller receives a safety flag and executes anyway. Separating detection probability $p_d$ from enforcement probability $p_e$ establishes that $p_e \approx 0$ by default across every framework we tested, making detection quality \emph{formally irrelevant} to security when enforcement is absent --- a finding consistent with the spontaneo