TikTok, a widely-used social media app boasting over a billion monthly active
Benutzer, erfordert eine effektive Qualitätssicherung der App für ihre komplexen Funktionen.
Funktionstests sind für die Erreichung dieses Ziels von entscheidender Bedeutung. Jedoch, the multi-user
interactive features within the app, wie zum Beispiel Live-Streaming, voice calls, usw.,
pose significant challenges for developers, who must handle simultaneous device
management and user interaction coordination. Um dies anzugehen, 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.

Dieser Artikel untersucht Zeitreisen und deren Auswirkungen.

PDF herunterladen: