A Decoupled Human-in-the-Loop System for Controlled Autonomy in Agentic Workflows

一种用于智能体工作流中受控自主性的解耦式“人在回路”系统

AI agents are increasingly deployed to execute tasks and make decisions within agentic workflows, introducing new requirements for safe and controlled autonomy. 人工智能体正越来越多地被部署在智能体工作流中以执行任务并做出决策，这为安全且受控的自主性提出了新的要求。

Prior work has established the importance of human oversight for ensuring transparency, accountability, and trustworthiness in such systems. However, existing implementations of Human-in-the-Loop (HITL) mechanisms are typically embedded within application logic, limiting reuse, consistency, and scalability across multi-agent environments. 先前的研究已经确立了人工监督对于确保此类系统的透明度、问责制和可信度的重要性。然而，现有的“人在回路”（HITL）机制实现通常嵌入在应用程序逻辑中，限制了其在多智能体环境中的复用性、一致性和可扩展性。

This paper presents a decoupled HITL system architecture that treats human oversight as an independent system component within the agent operating environment. The proposed design separates human interaction management from application workflows through explicit interfaces and a structured execution model. 本文提出了一种解耦的 HITL 系统架构，将人工监督视为智能体运行环境中的一个独立系统组件。该设计通过显式接口和结构化的执行模型，将人机交互管理与应用程序工作流分离开来。

In addition, a design framework is introduced to formalize HITL integration along four dimensions: intervention conditions, role resolution, interaction semantics, and communication channel. This framework enables selective and context-aware human involvement while maintaining system-level consistency. 此外，本文引入了一个设计框架，从干预条件、角色解析、交互语义和通信通道四个维度对 HITL 集成进行了规范化。该框架在保持系统级一致性的同时，实现了选择性的、具备上下文感知能力的人工参与。

The approach supports alignment with emerging agent communication protocols, allowing HITL to be implemented as a protocol-level concern. By externalizing HITL and structuring its integration, the system provides a foundation for scalable governance and progressive autonomy in agentic workflows. 该方法支持与新兴的智能体通信协议对齐，允许将 HITL 作为协议层面的关注点来实现。通过将 HITL 外部化并结构化其集成方式，该系统为智能体工作流中的可扩展治理和渐进式自主性奠定了基础。