# Managed Autonomy at Runtime: Gear-Based Safety and Governance for Single- and Multi-Agent Cyber-Physical Systems

arXiv: https://arxiv.org/abs/2607.00334 · HTML: https://mlsanity.com/paper/2607.00334/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 8 of its 30 references that are in the map.
- First posted on arXiv 1 Jul 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 8 of 8)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [The Off-Switch Game](https://mlsanity.com/paper/1611.08219/) (2016)
- [Levels of Autonomy for AI Agents](https://mlsanity.com/paper/2506.12469/) (2025)
- [Towards Verifiably Safe Tool Use for LLM Agents](https://mlsanity.com/paper/2601.08012/) (2026)
- [Intelligence as Managed Autonomy: Failure, Escalation, and Governance for Agentic AI Systems](https://mlsanity.com/paper/2605.27628/) (2026)

## Built on by (most cited first, 1 of 1)

- [The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agents](https://mlsanity.com/paper/2608.06663/) (2026)

## Abstract (arXiv)

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 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×, 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.