# Breaking Single-Tester Limits: Multi-Agent LLMs for Multi-User Feature Testing

arXiv: https://arxiv.org/abs/2506.17539 · HTML: https://mlsanity.com/paper/2506.17539/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in GUI and mobile agents, one of 16 directions in LLM agents and tool use.
- Builds on 29 of its 67 references that are in the map.
- First posted on arXiv 21 Jun 2025.

## Placed in

- LLM agents and tool use / [GUI and mobile agents](https://mlsanity.com/agents/gui-and-mobile-agents/)

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

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)](https://mlsanity.com/paper/2309.17421/) (2023)
- [AppAgent: Multimodal Agents as Smartphone Users](https://mlsanity.com/paper/2312.13771/) (2023)
- [Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception](https://mlsanity.com/paper/2401.16158/) (2024)
- [AutoDroid: LLM-powered Task Automation in Android](https://mlsanity.com/paper/2308.15272/) (2023)
- [Enabling Conversational Interaction with Mobile UI using Large Language Models](https://mlsanity.com/paper/2209.08655/) (2022)
- [A Dataset for Interactive Vision-Language Navigation with Unknown Command Feasibility](https://mlsanity.com/paper/2202.02312/) (2022)
- [Make LLM a Testing Expert: Bringing Human-like Interaction to Mobile GUI Testing via Functionality-aware Decisions](https://mlsanity.com/paper/2310.15780/) (2023)
- [Prompting Is All You Need: Automated Android Bug Replay with Large Language Models](https://mlsanity.com/paper/2306.01987/) (2023)
- [Fill in the Blank: Context-aware Automated Text Input Generation for Mobile GUI Testing](https://mlsanity.com/paper/2212.04732/) (2022)
- [Translating Video Recordings of Mobile App Usages into Replayable Scenarios](https://mlsanity.com/paper/2005.09057/) (2020)
- [Unveiling the Tricks: Automated Detection of Dark Patterns in Mobile Applications](https://mlsanity.com/paper/2308.05898/) (2023)
- [MUD: Towards a Large-Scale and Noise-Filtered UI Dataset for Modern Style UI Modeling](https://mlsanity.com/paper/2405.07090/) (2024)
- [WES: Agent-based User Interaction Simulation on Real Infrastructure](https://mlsanity.com/paper/2004.05363/) (2020)
- [Video2Action: Reducing Human Interactions in Action Annotation of App Tutorial Videos](https://mlsanity.com/paper/2308.03252/) (2023)
- [Feedback-Driven Automated Whole Bug Report Reproduction for Android Apps](https://mlsanity.com/paper/2407.05165/) (2024)
- [Enabling Cost-Effective UI Automation Testing with Retrieval-Based LLMs: A Case Study in WeChat](https://mlsanity.com/paper/2409.07829/) (2024)
- [GIFdroid: Automated Replay of Visual Bug Reports for Android Apps](https://mlsanity.com/paper/2112.04128/) (2021)
- [Gallery D.C.: Auto-created GUI Component Gallery for Design Search and Knowledge Discovery](https://mlsanity.com/paper/2204.06700/) (2022)
- [Psychologically-Inspired, Unsupervised Inference of Perceptual Groups of GUI Widgets from GUI Images](https://mlsanity.com/paper/2206.10352/) (2022)
- [Agent for User: Testing Multi-User Interactive Features in TikTok](https://mlsanity.com/paper/2504.15474/) (2025)
- [From Lost to Found: Discover Missing UI Design Semantics through Recovering Missing Tags](https://mlsanity.com/paper/2008.06895/) (2020)
- [An Empirical Study on Leveraging Images in Automated Bug Report Reproduction](https://mlsanity.com/paper/2502.15099/) (2025)
- [Auto-Icon+: An Automated End-to-End Code Generation Tool for Icon Designs in UI Development](https://mlsanity.com/paper/2204.08676/) (2022)
- [Read It, Don't Watch It: Captioning Bug Recordings Automatically](https://mlsanity.com/paper/2302.00886/) (2023)
- [Towards Efficient Record and Replay: A Case Study in WeChat](https://mlsanity.com/paper/2308.06657/) (2023)
- [Efficiency Matters: Speeding Up Automated Testing with GUI Rendering Inference](https://mlsanity.com/paper/2212.05203/) (2022)

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

- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)

## Abstract (arXiv)

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.