让智能体响应中的各组件独立受控，避免因依赖失效导致整体失败。
HALO: Heterogeneous Admission through Localized Obligations for Safe Agentic Execution
- 为异构响应设计局部化依赖检查机制，仅丢弃不满足前提的组件。
- 在248个测试组件中保留全部支持项，整响应策略仅保留0个。
- 适合需要高可靠性的自主系统，如无人机路径规划与恢复场景。
近期的智能体AI系统可能返回包含通知、请求、转交和动作的异构响应。在外部使用前条件可能变化，因此同一响应中的组件未必仍需共同维持支持。拒绝整个响应会丢弃有用部分，而独立检查组件可能导致依赖缺失。我们提出异构准入与局部义务（HALO）运行时协议：保留其声明前提仍被支持的组件，精确重检每个动作后才派发，并允许被阻塞的动作仅由新候选替换。HALO匹配全部96项准入预期，通过所有20项协议测试。在结构化响应回放中，保留了248/248个支持组件，包括128/128不受无关变更影响的组件，而整响应策略仅保留0/248。在十次冷启动PX4/Gazebo会话中，HALO成功阻止所有测试过的过期路径，未观测到匹配的过期设定点，并完成所有新恢复任务。
原文摘要 · Abstract (English)
Recent agentic AI systems may return a heterogeneous response containing notices, requests, handoffs, and actions. Conditions can change before external use, so components from the same response need not remain supported together. Rejecting the whole response discards useful components, whereas checking components independently can leave a dependent without its prerequisite. We present Heterogeneous Admission with Localized Obligations (HALO), a runtime protocol that preserves supported components whose declared prerequisites also remain supported, rechecks each exact action before dispatch, and allows blocked actions to be replaced only by fresh candidates. HALO matched all 96 admission expectations and passed all 20 protocol tests. In structured-response replay, it retained 248/248 supported components, including 128/128 unaffected by unrelated changes, while a whole-response policy retained 0/248. Across ten cold-start PX4/Gazebo sessions, HALO blocked every tested stale route, observed no matching stale setpoint, and completed all fresh recoveries.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。