ADF-EA：面向智能体设备基础的一种统一执行保障系统
ADF-EA: A Unified Execution Assurance System for Agent Device Foundation
- Huawei（华为）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出ADF-EA架构，通过设备能力契约统一规划与执行，实现基于证据的验证和授权恢复，减少虚假完成并支持状态修复，提升异构设备上的智能体执行可靠性。
AI中文摘要：
基于大语言模型（LLM）的智能体可以通过工具和API访问异构设备，但可靠执行必须考虑未达成的效果、不确定的结果以及不断变化的前提条件。一个命令可能被确认接收却未产生预期效果，而缺失的反馈可能掩盖已经成功的动作。我们提出了智能体设备基础——执行保障（ADF-EA），一种通过共享能力契约连接智能体规划与设备执行的架构。设备能力契约（DCCs）统一了异构接口上的调用条件、预期效果、证据要求和恢复规则。智能体利用这些契约进行规划，而运行时则应用相同的语义来授权动作、验证效果并管理继续与完成。持久执行状态在计划修订之间保留已验证的进度、未解决的结果和剩余预算，从而实现基于观察的恢复、授权的重试以及必要的状态修复。我们形式化了执行生命周期，并为完成和恢复授权建立了条件可靠性属性。评估涵盖多个LLM、五个智能体框架以及模拟的过程控制、家庭和机器人操作领域。与直接调用和现有的执行检查方法相比，ADF-EA减少了虚假完成和不必要的重复，支持必要的状态修复，防止调用不可用的能力，并保留允许的任务完成和恢复。这些结果证明了DCCs作为跨异构设备智能体自治的可复用语义基础，在单一架构中统一了基于能力的规划、基于证据的执行和授权的恢复。
英文摘要：
Agents based on large language models (LLMs) can access heterogeneous devices through tools and APIs, but reliable execution must account for unmet effects, uncertain outcomes, and changing prerequisites. A command may be acknowledged without producing its intended effect, while missing feedback may obscure an action that has already succeeded. We present Agent Device Foundation--Execution Assurance (ADF-EA), an architecture that connects agent planning and device execution through shared capability contracts. Device Capability Contracts (DCCs) unify invocation conditions, intended effects, evidence requirements, and recovery rules across heterogeneous interfaces. Agents use these contracts to plan, while the runtime applies the same semantics to authorize actions, verify effects, and govern continuation and completion. Persistent execution state retains verified progress, unresolved outcomes, and remaining budgets across plan revisions, enabling observation-based recovery, authorized retries, and necessary state repair. We formalize the execution lifecycle and establish conditional soundness properties for completion and recovery authorization. Evaluations span multiple LLMs, five agent frameworks, and simulated process-control, household, and robotic manipulation domains. Compared with direct invocation and existing execution-checking approaches, ADF-EA reduces false completion and unnecessary repetition, supports necessary state repair, prevents calls to unavailable capabilities, and preserves permitted task completion and recovery. These results demonstrate DCCs as a reusable semantic foundation for agent autonomy across heterogeneous devices, unifying capability-based planning, evidence-grounded execution, and authorized recovery within one architecture.
