# Agent-Integrated Software: Interaction Contracts and Continuous Assurance

arXiv: https://arxiv.org/abs/2609.11381 · HTML: https://mlsanity.com/paper/2609.11381/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 54 references that are in the map.
- First posted on arXiv 10 Sep 2026.

## Builds on (most cited first, 29 of 29)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs](https://mlsanity.com/paper/2304.08244/) (2023)
- [AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents](https://mlsanity.com/paper/2405.14573/) (2024)
- [AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents](https://mlsanity.com/paper/2407.18901/) (2024)
- [ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities](https://mlsanity.com/paper/2408.04682/) (2024)
- [AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents](https://mlsanity.com/paper/2503.18666/) (2025)
- [AutoDroid: LLM-powered Task Automation in Android](https://mlsanity.com/paper/2308.15272/) (2023)
- [ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing](https://mlsanity.com/paper/2309.09128/) (2023)
- [CRMArena: Understanding the Capacity of LLM Agents to Perform Professional CRM Tasks in Realistic Environments](https://mlsanity.com/paper/2411.02305/) (2024)
- [Interactive Debugging and Steering of Multi-Agent AI Systems](https://mlsanity.com/paper/2503.02068/) (2025)
- [Large Language Models Empowered Personalized Web Agents](https://mlsanity.com/paper/2410.17236/) (2024)
- [Plan-Then-Execute: An Empirical Study of User Trust and Team Performance When Using LLM Agents As A Daily Assistant](https://mlsanity.com/paper/2502.01390/) (2025)
- [AgentOps: Enabling Observability of LLM Agents](https://mlsanity.com/paper/2411.05285/) (2024)
- [Lost in Simulation: LLM-Simulated Users are Unreliable Proxies for Human Users in Agentic Evaluations](https://mlsanity.com/paper/2601.17087/) (2026)
- [Cocoa: Co-Planning and Co-Execution with AI Agents](https://mlsanity.com/paper/2412.10999/) (2024)
- [τ-Knowledge: Evaluating Conversational Agents over Unstructured Knowledge](https://mlsanity.com/paper/2603.04370/) (2026)
- [LLM for Test Script Generation and Migration: Challenges, Capabilities, and Opportunities](https://mlsanity.com/paper/2309.13574/) (2023)
- [Building Your Own Product Copilot: Challenges, Opportunities, and Needs](https://mlsanity.com/paper/2312.14231/) (2023)
- [DroidCall: A Dataset for LLM-powered Android Intent Invocation](https://mlsanity.com/paper/2412.00402/) (2024)
- [Layout and Image Recognition Driving Cross-Platform Automated Mobile Testing](https://mlsanity.com/paper/2008.05182/) (2020)
- [Scenario-Guided LLM-based Mobile App GUI Testing](https://mlsanity.com/paper/2506.05079/) (2025)
- [From Cool Demos to Production-Ready FMware: Core Challenges and a Technology Roadmap](https://mlsanity.com/paper/2410.20791/) (2024)
- [Test Script Intention Generation for Mobile Application via GUI Image and Code Understanding](https://mlsanity.com/paper/2107.05165/) (2021)
- [Software Engineering for and with GUI Agent](https://mlsanity.com/paper/2608.09278/) (2026)

## Built on by (most cited first, 1 of 1)

- [From Agent Output to Authorized Transition](https://mlsanity.com/paper/2609.28216/) (2026)

## Abstract (arXiv)

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.