智能体集成软件：交互契约与持续保障

中文摘要 AI 辅助

将智能体嵌入现有应用程序会带来一个持续的协调问题：在委托执行继续进行的同时，用户可能修改目标并操作共享对象。我们认为，可靠的集成需要在任务级交互与应用行为之间建立显式的对应关系。我们提出智能体集成软件（Agent-Integrated Software, AIS）作为一种软件模式，它结合了传统核心、直接交互和内置智能体，并提出意图级交互抽象（Intent-Level Interaction Abstraction, IIA）作为任务语义，用户通过它来检查和管控委托工作。一个开放转换系统模型将AIS执行与IIA状态和事件关联起来。交互契约通过任务绑定、角色特定权限、控制转换和结果证据来约束这种关系；持续保障则在依赖关系变化时维护有范围限定的声明。一个紧凑的披露契约和条件命题说明了为何局部组件有效性不足，以及如何将选定的准入不变量与规划分离。对比不同的软件领域揭示了该框架的假设与局限。这一视角发展了一个研究议程，涵盖应用抽象、开发支持、受控执行、质量评估和人类监督，旨在使智能体集成成为一门可维护的软件工程学科。

英文摘要

Embedding an intelligent agent in an existing application creates a persistent coordination problem: users can revise goals and manipulate shared objects while delegated execution continues. We argue that dependable integration requires an explicit correspondence between task-level interaction and application behavior. We introduce Agent-Integrated Software (AIS) as a software pattern combining a conventional core, direct interaction, and a built-in agent, and Intent-Level Interaction Abstraction (IIA) as the task semantics through which users inspect and control delegated work. An open transition-system model relates AIS execution to IIA states and events. Interaction contracts constrain this relation through task bindings, role-specific authority, control transitions, and outcome evidence; continuous assurance maintains scoped claims as their dependencies change. A compact disclosure contract and conditional propositions illustrate why local component validity is insufficient and how selected admission invariants can be separated from planning. Contrasting software domains expose the framework's assumptions and limits. This perspective develops a research agenda spanning application abstraction, development support, controlled execution, quality assessment, and human supervision, with the aim of making agent integration a maintainable software engineering discipline.

发表机构

• Technical University of Munich（慕尼黑工业大学）
• Nanjing University（南京大学）

机构由 AI 辅助整理，请以论文原文为准。