任务状态治理：用于可验证和可恢复的GUI智能体执行的虚拟机
Task-State Governance: A Virtual Machine for Verifiable and Recoverable GUI Agent Execution
AI总结：
本研究提出任务状态治理交互范式，将任务表示为关联期望结果等的可编辑契约，实现为TaskVM，经实验验证可提升契约合规性、用户恢复控制与信任度，同时保持执行结果不变。
摘要：
图形用户界面（GUI）智能体如今可在真实应用中执行工作流，但当执行出现偏差时，用户必须确定发生了什么变化、哪些内容本应保持不变以及哪些内容仍可恢复。以计划为中心的界面让用户监督流程，但用户需承受应用状态的变更。我们提出任务状态治理这一交互范式，它将任务表示为可编辑的契约，关联期望结果、必须保留的事实以及观测到的应用状态。我们将该范式实例化为TaskVM，它将实时状态映射为可编辑的任务控件，将用户编辑操作作为真实的界面动作执行，通过独立观测验证结果，并将每个动作标记为可逆转、可补偿或不可逆转。在自动化契约基准、受控用户研究以及开放的实时模型探索中，该范式提升了契约合规性、用户的恢复控制能力和信任度，同时保持执行结果不变。任务契约为可治理的智能体界面开辟了设计空间。
英文摘要：
Graphical user interface (GUI) agents now execute workflows across real applications, but when execution drifts, users must determine what changed, what should have remained untouched, and what can still be recovered. Plan-centric interfaces leave users supervising procedure, but users live with changes to application state. We introduce task-state governance, an interaction paradigm that represents a task as an editable contract linking desired outcomes, facts that must be preserved, and observed application state. We instantiate this paradigm in TaskVM, which projects live state into editable task controls, executes user edits as genuine interface actions, verifies outcomes through independent observation, and marks each action as reversible, compensatable, or irreversible. Across an automated contract benchmark, a controlled user study, and an open live-model exploration, the paradigm strengthened contract compliance and users' recovery control and trust, while execution outcomes were held constant. Task contracts open a design space for governable agent interfaces.
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。
