Intelligence as Managed Autonomy: Failure, Escalation, and Governance for Agenti

arXiv:2605.12963v1 Announce Type: new Abstract: As AI systems become increasingly capable, safety strategies must be evaluated not only by how much they reduce present risk, but

arXiv:2604.23280v1 Announce Type: new Abstract: AI agents are now running real transactions, workflows, and sub-agent chains across organizational boundaries without continuous

arXiv:2607.18243v1 Announce Type: new Abstract: Agentic AI is crossing trust boundaries faster than current risk models can represent. Existing approaches provide one of two

arXiv:2604.05229v1 Announce Type: new Abstract: Agentic AI systems plan, use tools, maintain state, and produce multi-step trajectories with external effects. Those properties

arXiv:2605.00055v1 Announce Type: cross Abstract: We report a safety incident in a deployed multi-agent research system in which a primary AI agent installed 107 unauthorized

As AI agents increasingly work alongside humans across organizations, companies could be inadvertently opening a new attack surface. Insecure agents can be manipulated to access

arXiv:2605.22842v1 Announce Type: cross Abstract: Multi-agent AI pipelines typically assume that agent misconduct originates from model misalignment. We identify a structural

arXiv:2604.27292v1 Announce Type: new Abstract: Every system that performs effects has two boundaries: what it can do (expressiveness) and what governance covers (governance). In