arXiv 2604.111742026-04-13cs.ROcs.AI

EmbodiedGovBench: 一种用于具身代理系统治理、恢复和升级安全性的基准

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

School of Software, Harbin Institute of Technology（哈尔滨工业大学软件学院）；School of Computer Science and Technology, Harbin Institute of Technology（哈尔滨工业大学计算机科学与技术学院）；School of Mathematical and Computer Sciences, Heriot-Watt University, Malaysia Campus（赫瑞-瓦特大学马来西亚校区数学与计算机科学学院）；School of Future Science and Engineering, Soochow University（苏州大学未来科学与工程学院）

Xue Qin, Simin Luan, John See, Cong Yang, Zhijun Li

备注：: 34 pages, 7 tables. Code: https://github.com/s20sc/embodied-gov-bench

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出EmbodiedGovBench基准，用于评估具身代理系统的治理能力，包括可控性、政策边界、安全恢复和审计完整性等，填补了传统任务成功率指标的不足。

摘要：

近期具身AI的进步催生了机器人策略、基础模型和模块化运行时的生态系统。然而，当前评估仍受任务成功率等指标主导，无法衡量具身系统是否具备治理能力。本文提出的EmbodiedGovBench基准用于评估具身代理系统的治理性能，涵盖七种治理维度：未经授权的能力调用、运行时漂移鲁棒性、恢复成功率、政策可移植性、版本升级安全性、人类接管响应性和审计完整性。该基准覆盖单机器人和舰队设置，包含场景模板、扰动操作符、治理指标和基线评估协议，并描述了如何在具有模块化接口的具身能力运行时上实例化该基准。分析表明，具身治理应成为首要评估目标，EmbodiedGovBench提供了这一转变的初始测量框架。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。