AI Agents 相关度: 9/10

Governed Capability Evolution for Embodied Agents: Safe Upgrade, Compatibility Checking, and Runtime Rollback for Embodied Capability Modules

Xue Qin, Simin Luan, John See, Cong Yang, Zhijun Li
arXiv: 2604.08059v1 发布: 2026-04-09 更新: 2026-04-09

AI 摘要

提出一种受控的具身智能体能力进化框架,保障能力升级的安全性、兼容性和回滚机制。

主要贡献

  • 提出了具身智能体能力进化的系统问题,关注安全部署和恢复。
  • 提出了一个生命周期感知的升级框架,包含验证、评估、部署、监控和回滚等阶段。
  • 定义了四种升级兼容性检查:接口、策略、行为和恢复。

方法论

构建一个包含验证、沙箱评估、影子部署、门控激活、在线监控和回滚的运行时流水线,并进行实验验证。

原文摘要

Embodied agents are increasingly expected to improve over time by updating their executable capabilities rather than rewriting the agent itself. Prior work has separately studied modular capability packaging, capability evolution, and runtime governance. However, a key systems problem remains underexplored: once an embodied capability module evolves into a new version, how can the hosting system deploy it safely without breaking policy constraints, execution assumptions, or recovery guarantees? We formulate governed capability evolution as a first-class systems problem for embodied agents. We propose a lifecycle-aware upgrade framework in which every new capability version is treated as a governed deployment candidate rather than an immediately executable replacement. The framework introduces four upgrade compatibility checks -- interface, policy, behavioral, and recovery -- and organizes them into a staged runtime pipeline comprising candidate validation, sandbox evaluation, shadow deployment, gated activation, online monitoring, and rollback. We evaluate over 6 rounds of capability upgrade with 15 random seeds. Naive upgrade achieves 72.9% task success but drives unsafe activation to 60% by the final round; governed upgrade retains comparable success (67.4%) while maintaining zero unsafe activations across all rounds (Wilcoxon p=0.003). Shadow deployment reveals 40% of regressions invisible to sandbox evaluation alone, and rollback succeeds in 79.8% of post-activation drift scenarios.

标签

具身智能体 能力进化 安全升级 运行时治理 模块化

arXiv 分类

cs.RO cs.AI