# Harnessing Embodied Agents: Runtime Governance for Policy-Constrained Execution

arXiv: https://arxiv.org/abs/2604.07833 · HTML: https://mlsanity.com/paper/2604.07833/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Apr 2026.

## Built on by (most cited first, 7 of 7)

- [OpenClawBench: Benchmarking Process-side Anomalies in Real-world Agent Execution Trajectories](https://mlsanity.com/paper/2605.29253/) (2026)
- [Harness Engineering for Physical AI: Robot Middleware Is the Harness Layer](https://mlsanity.com/paper/2606.09416/) (2026)
- [EmbodiedGovBench: A Benchmark for Governance, Recovery, and Upgrade Safety in Embodied Agent Systems](https://mlsanity.com/paper/2604.11174/) (2026)
- [ECM Contracts: Contract-Aware, Versioned, and Governable Capability Interfaces for Embodied Agents](https://mlsanity.com/paper/2604.13097/) (2026)
- [Federated Single-Agent Robotics: Multi-Robot Coordination Without Intra-Robot Multi-Agent Fragmentation](https://mlsanity.com/paper/2604.11028/) (2026)
- [Towards Trustworthy Embodied Intelligence: A Systems Framework and Graded Trustworthiness Levels](https://mlsanity.com/paper/2607.26121/) (2026)
- [Epi-Logic: A Conceptual Framework for Epistemic Runtime Control, Schema Validity Checking, and Controlled Accommodation in Autonomous AI Agents](https://mlsanity.com/paper/2609.24755/) (2026)

## Abstract (arXiv)

Embodied Agents are evolving from passive reasoning systems into active executors that interact with tools, robots, and physical environments. Once an agent gains execution authority, the central challenge shifts from how to make it act to how to keep its actions governable at runtime. Existing approaches embed safety, recovery, and decision constraints inside the agent loop, making execution control difficult to standardize, audit, and adapt across environments. We propose a runtime governance framework for policy-constrained execution that separates agent cognition from execution oversight. Governance is externalized into a dedicated runtime layer performing policy checking, capability admission, execution monitoring, rollback, and human override. We formalize the control boundary among a persistent Embodied Agent, modular Capability Packages, and the governance layer, and define a policy-constrained execution pipeline evaluated under controlled simulation. Over 1000 randomized trials, the framework achieves 96.2%+/-2.7% interception of unauthorized actions, reduces unsafe continuation from 100% to 22.2%+/-3.1% under runtime drift, and attains 90.7%+/-3.0% recovery success with full policy compliance. Comparison with five baselines, including AutoRT-style constitution filtering and RoboGuard-style two-stage guardrails, shows that pre-execution filtering is equally effective across governance-aware methods, while only the proposed framework provides continuous runtime detection (RVDR = 61.3% vs. 0%) and structured recovery (all p<0.001). A sensitivity sweep across the full detection range confirms a genuine detection-continuation trade-off. This work argues future embodied systems should be designed for governable execution.