Harnessing Embodied Agents: Runtime Governance for Policy-Constrained Execution
Xue Qin, Simin Luan, John See, Cong Yang, Zhijun Li

TL;DR
This paper introduces a runtime governance framework for embodied agents, separating cognition from oversight to improve safety, control, and compliance during physical interactions.
Contribution
It formalizes a policy-constrained execution architecture with externalized governance, enhancing safety and auditability of embodied agents compared to embedded approaches.
Findings
96.2% interception of unauthorized actions
Reduced unsafe continuation from 100% to 22.2% under runtime drift
91.4% recovery success with full policy compliance
Abstract
Embodied agents are evolving from passive reasoning systems into active executors that interact with tools, robots, and physical environments. Once granted execution authority, the central challenge becomes how to keep actions governable at runtime. Existing approaches embed safety and recovery logic inside the agent loop, making execution control difficult to standardize, audit, and adapt. This paper argues that embodied intelligence requires not only stronger agents, but stronger runtime governance. We propose a 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 handling, and human override. We formalize the control boundary among the embodied agent, Embodied Capability Modules (ECMs), and…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
