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

Jul 16, 2026

Upload by Eliana

Autonomous agents, from LLM-driven software to robotic physical platforms, encounter safety violations, behavioral instability, and continuity loss when operating without continuous human oversight. EntropyRuntime introduces a discrete-time control system with five execution gears—OBSERVE, SUGGEST, PLAN, EXECUTE, and INTEGRATE—combined with utility-gated dispatch and event-driven fallback. For single agents, it proves monotonic stability, execution safety, eventual stabilization, fallback completeness, and equivalence to a gear-constrained MDP. For multi-agent CPS, SMARt governance states, consensus gating, and swarm Lyapunov analysis provide distributed stability and zero-collision safety, demonstrated on a three-agent UR5 assembly cell with a 99.6% anomaly detection rate and formal workspace certificates.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages18

Reading Time45 min

Introduction

Failure modes of autonomous agents

EntropyRuntime and gear-based action control

SMARt runtime governance states and enforcement

Contributions and evaluation overview

Managed Autonomy at Runtime: Gear-Based Safety and Governance for Single-and Multi-Agent Cyber-Physical Systems arXiv :2607 .00334v 1 [ cs .AI] 1 Jul 2026 Srini Ramaswamy CEO & AI Strategist [DNRS.ai](DNRS.ai), USA [srini@computer.org](srini@computer.org) Wang Miaosheng Independent Researcher ORCID: 0009-0003-2767-2421 [wmsmiaosheng@outlook.com](wmsmiaosheng@outlook.com) 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 EntropyRuntime, a discrete-time control system that combines five execution gears (OBSERVE, SUGGEST, PLAN, EXECUTE, INTEGRATE) 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-COGNITIVE/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 singleagent 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. Keywords: managed autonomy, AI governance, autonomous agents, runtime verification, gear-based safety, utility gating, multi-agent systems, cyber-physical systems, Lyapunov stability, robotic assembly 1 Introduction The emergence of large language model (LLM) agents capable of multi-step reasoning, tool use, and environment interaction has created a new class of autonomous systems [1, 2] . These agents operate inclosed loops that receive observations, generate plans, execute actions via external tools, and incorporate feedback, often without requiring human approval for each step. Simultaneously, robotic and cyber-physical agents increasingly operate in shared physical workspaces where sensor faults, coordination failures, and unsafe actions carry immediate physical consequences. Both settings share a structural problem: the agent’s autonomy is granted in a binary and static fashion, with no principled mechanism for dynamically adjusting the scope of permissible actions in response to observed safety signals. Autonomous agents face three interrelated failure modes. First, safety violations: the agent may issue actions that produce irreversible side effects without adequate verification [3] . Second, behavioral instability: the agent may oscillate between strategies, fail to converge, or enter degenerate loops [4] . Third, continuity loss: the agent may halt unexpectedly, losing accumulated context and requiring costly manual restarts. In multi-agent CPS, a fourth failure mode emerges: coordination blindness, where one agent’s sensor fault carries consequences for all neighbors yet the per-agent control layer is structurally incapable of detecting or responding to it. We develop EntropyRuntime to address these failure modes through gear-based action control. At each cycle, one of five gears limits the scope and impact of permissible actions, and a utility gate evaluates every candidate before dispatch. For

FAQs

What core problem does EntropyRuntime target in autonomous agents?

It targets safety violations from unverified actions, behavioral instability from unconstrained loops, and continuity loss from unhandled error states. For multi-agent CPS, it also addresses coordination blindness when one agent’s sensor fault affects neighbors.

How does EntropyRuntime use “execution gears” to control autonomy?

Each cycle selects one of five gears—OBSERVE, SUGGEST, PLAN, EXECUTE, and INTEGRATE—to limit the scope and impact of permissible actions. A utility gate evaluates candidate actions before dispatch.

What guarantees are provided for single-agent and multi-agent CPS settings?

For single agents, the paper proves monotonic stability, execution safety (no negative-utility action is dispatched), eventual stabilization, fallback completeness, and an equivalence to a gear-constrained MDP. For multi-agent CPS, SMARt governance states plus consensus gating, swarm Lyapunov analysis, per-agent gear authority, and rendezvous control yield distributed safety and zero collision under stated assumptions.

Jul 16, 2026

Upload by Eliana