一句话：提出 MAdroid，用 LLM 驱动的多智能体协作自动化移动应用多用户交互功能的测试。
移动应用中聊天通话、直播、视频会议等多用户交互功能日益重要，但其测试需要及时、动态且协同的多方用户交互，现有自动化测试方法难以胜任。受自主协作智能体思想的启发，论文提出 MAdroid：一种由大语言模型驱动的多智能体方法，用于自动化多用户交互任务的应用功能测试。MAdroid 包含两类功能性智能体：用户智能体（Operator）与监督智能体（Coordinator 和 Observer），其中 Coordinator 负责指挥交互任务，Operator 在设备上模拟用户操作，Observer 监控并审查任务自动化过程。作者在 41 个多用户交互任务上进行评估，任务完成率达 82.9%，动作相似度达 96.8%，优于消融实验与当前最优基线；初步研究还通过回归测试发现 11 个多用户交互缺陷，验证了其在真实开发场景中的实用价值。
The growing dependence on mobile phones and their apps has made multi-user interactive features—like chat calls, live streaming, and video conferencing—indispensable for bridging the gaps in social connectivity caused by physical and situational barriers. However, automating these interactive features for testing is fraught with challenges, owing to their inherent need for timely, dynamic, and collaborative user interactions, which current automated testing methods inadequately address. Inspired by the concept of agents designed to autonomously and collaboratively tackle problems, we propose MAdroid, a novel multi-agent approach powered by the Large Language Models (LLMs) to automate the multi-user interactive task for app feature testing. Specifically, MAdroid employs two functional types of multi-agents: user agents (Operator) and supervisor agents (Coordinator and Observer). Each agent takes a specific role: the Coordinator directs the interactive task; the Operator mimics user interactions on the device; and the Observer monitors and reviews the task automation process. Our evaluation, which included 41 multi-user interactive tasks, demonstrates the effectiveness of our approach, achieving 82.9% of the tasks with 96.8% action similarity, outperforming the ablation studies and state-of-the-art baselines. Additionally, a preliminary investigation underscores MAdroid’s practicality by helping identify 11 multi-user interactive bugs during regression app testing, confirming its potential value in real-world software development contexts.
@inproceedings{abs-2506-17539,
title = {Breaking Single-Tester Limits: Multi-Agent LLMs for Multi-User Feature Testing},
author = {Sidong Feng and Changhao Du and Huaxiao Liu and Qingnan Wang and Zhengwei Lv and Mengfei Wang and Chunyang Chen},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3744916.3764535}
}