Skip to content
Agents

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

arXiv:2609.15293v3 Announce Type: replace Abstract: 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-flo

arXiv cs.AIResearch source·