# Agent for User: Testing Multi-User Interactive Features in TikTok

arXiv: https://arxiv.org/abs/2504.15474 · HTML: https://mlsanity.com/paper/2504.15474/

## Key facts

- Cited by 5 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 18 of its 57 references that are in the map.
- First posted on arXiv 21 Apr 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, 18 of 18)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)](https://mlsanity.com/paper/2309.17421/) (2023)
- [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)
- [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)
- [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)
- [How do Developers Test Android Applications?](https://mlsanity.com/paper/1801.06268/) (2018)
- [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)
- [An Empirical Study on Leveraging Images in Automated Bug Report Reproduction](https://mlsanity.com/paper/2502.15099/) (2025)
- [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)
- [Agent-Based Software Testing: A Definition and Systematic Mapping Study](https://mlsanity.com/paper/2007.10224/) (2020)
- [Efficiency Matters: Speeding Up Automated Testing with GUI Rendering Inference](https://mlsanity.com/paper/2212.05203/) (2022)

## Built on by (most cited first, 5 of 5)

- [Breaking Single-Tester Limits: Multi-Agent LLMs for Multi-User Feature Testing](https://mlsanity.com/paper/2506.17539/) (2025)
- [GUISpector: An MLLM Agent Framework for Automated Verification of Natural Language Requirements in GUI Prototypes](https://mlsanity.com/paper/2510.04791/) (2025)
- [SwipeGen: Bridging the Execution Gap in GUI Agents via Human-like Swipe Synthesis](https://mlsanity.com/paper/2601.18305/) (2026)
- [LikeThis! Empowering App Users to Submit UI Improvement Suggestions Instead of Complaints](https://mlsanity.com/paper/2603.04245/) (2026)
- [Developing a Roadmap to an AI-first Organization: A Case Study in Embedded Software Development](https://mlsanity.com/paper/2609.30863/) (2026)

## Abstract (arXiv)

TikTok, a widely-used social media app boasting over a billion monthly active users, requires effective app quality assurance for its intricate features. Feature testing is crucial in achieving this goal. However, the multi-user interactive features within the app, such as live streaming, voice calls, etc., pose significant challenges for developers, who must handle simultaneous device management and user interaction coordination. To address this, we introduce a novel multi-agent approach, powered by the Large Language Models (LLMs), to automate the testing of multi-user interactive app features. In detail, we build a virtual device farm that allocates the necessary number of devices for a given multi-user interactive task. For each device, we deploy an LLM-based agent that simulates a user, thereby mimicking user interactions to collaboratively automate the testing process. The evaluations on 24 multi-user interactive tasks within the TikTok app, showcase its capability to cover 75% of tasks with 85.9% action similarity and offer 87% time savings for developers. Additionally, we have also integrated our approach into the real-world TikTok testing platform, aiding in the detection of 26 multi-user interactive bugs.