EmbodiedGovBench: A Benchmark for Governance, Recovery, and Upgrade Safety in Embodied Agent Systems

2026-04-13

AI Summary

This work addresses a critical gap in the evaluation of embodied intelligent systems, which has predominantly focused on task success rates while neglecting governance capabilities—such as policy compliance, safety recovery, and responsiveness to human intervention. To remedy this, the study introduces governance capability as a first-class evaluation objective and proposes a comprehensive benchmark encompassing seven dimensions, including controllability, recoverability, and evolutionary safety. The framework supports standardized testing in both single-agent and multi-agent environments through a modular runtime architecture, contract-aware upgrade mechanisms, scenario templates, and perturbation operators. By providing a complete suite of metrics and baseline protocols, this benchmark establishes a quantitative foundation for the safe and controllable advancement of embodied intelligent systems.

Technology Category

• Intelligent Robots: Embodied AI
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness
• Multiagent Systems: Adversarial Agents

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Recent progress in embodied AI has produced a growing ecosystem of robot policies, foundation models, and modular runtimes. However, current evaluation remains dominated by task success metrics such as completion rate or manipulation accuracy. These metrics leave a critical gap: they do not measure whether embodied systems are governable -- whether they respect capability boundaries, enforce policies, recover safely, maintain audit trails, and respond to human oversight. We present EmbodiedGovBench, a benchmark for governance-oriented evaluation of embodied agent systems. Rather than asking only whether a robot can complete a task, EmbodiedGovBench evaluates whether the system remains controllable, policy-bounded, recoverable, auditable, and evolution-safe under realistic perturbations. The benchmark covers seven governance dimensions: unauthorized capability invocation, runtime drift robustness, recovery success, policy portability, version upgrade safety, human override responsiveness, and audit completeness. We define a benchmark structure spanning single-robot and fleet settings, with scenario templates, perturbation operators, governance metrics, and baseline evaluation protocols. We describe how the benchmark can be instantiated over embodied capability runtimes with modular interfaces and contract-aware upgrade workflows. Our analysis suggests that embodied governance should become a first-class evaluation target. EmbodiedGovBench provides the initial measurement framework for that shift.

Problem

• embodied AI
• governance
• benchmark
• safety
• recoverability

Innovation

• embodied governance
• safety benchmark
• policy enforcement
• recovery robustness
• upgrade safety