{"ID":5551889,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-04T01:45:22.703757252Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.00334","arxiv_id":"2607.00334","title":"Managed Autonomy at Runtime: Gear-Based Safety and Governance for Single- and Multi-Agent Cyber-Physical Systems","abstract":"Autonomous agents, whether LLM-driven software agents or robotic physical agents, face a common class of failure modes when operating without continuous human oversight: safety violations from unverified actions, behavioral instability from unconstrained loops, and continuity loss from unhandled error states. We develop \\system{}, a discrete-time control system that combines five execution gears (\\Gobs{}, \\Gsug{}, \\Gplan{}, \\Gexec{}, \\Gint{}) with utility-gated dispatch and event-driven fallback. For the single-agent case, we prove monotonic stability, execution safety, eventual stabilization, fallback completeness, and equivalence to a gear-constrained Markov decision process. For multi-agent cyber-physical systems (CPS), we apply the established \\smart{} managed-autonomy lifecycle and map runtime evidence into its four governance states (\\Stable{}/\\Meta{}/\\Assisted{}/\\Regulated{}). Consensus gating, swarm-level Lyapunov analysis, per-agent gear authority, and rendezvous control provide distributed safety and stability guarantees, including zero collision under the stated assumptions. We evaluate the resulting runtime on a three-agent UR5 robotic assembly cell using fault magnitudes calibrated from the NIST \\emph{Degradation Measurement of Robot Arm Position Accuracy} dataset across 10,000 Monte Carlo episodes. It achieves a 99.6\\% anomaly detection rate versus 2.1\\% for the single-agent baseline, reduces detection latency by $3.5\\times$, and supplies a formal physical-workspace safety certificate. The execution gears act as micro-level permissions beneath the \\smart{} runtime governance states, separating action control from autonomy governance.","short_abstract":"Autonomous agents, whether LLM-driven software agents or robotic physical agents, face a common class of failure modes when operating without continuous human oversight: safety violations from unverified actions, behavioral instability from unconstrained loops, and continuity loss from unhandled error states. We develo...","url_abs":"https://arxiv.org/abs/2607.00334","url_pdf":"https://arxiv.org/pdf/2607.00334v1","authors":"[\"Srini Ramaswamy\",\"Wang Miaosheng\"]","published":"2026-07-01T02:21:38Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\"]","has_code":false}