Agent-Integrated Software: Interaction Contracts and Continuous Assurance
Shengcheng Yu (Technical University of Munich), Chunrong Fang and Zhenyu Chen (Nanjing University) propose Agent-Integrated Software, a pattern and formal model for applications with a built-in agent that users can inspect and redirect while it works.
Ask this paper
Problem: When an agent is embedded in an application, users can change goals and edit shared objects while delegated work is still running.
Abstractions: Agent-Integrated Software combines a conventional core, direct interaction and a built-in agent. Intent-Level Interaction Abstraction gives users task-level states to inspect and control.
Interaction contracts: Contracts constrain the link between agent execution and task states through task bindings, role-specific authority, control transitions and outcome evidence.
Continuous assurance: Claims about the system are kept valid as their dependencies change, and the paper sets out a research agenda for agent integration as a software engineering discipline.
Abstract
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.