Tik Tok, a widely-used social media app boasting over a billion monthly active
utilisateurs, nécessite une assurance qualité efficace de l'application pour ses fonctionnalités complexes.
Les tests de fonctionnalités sont cruciaux pour atteindre cet objectif. Cependant, the multi-user
interactive features within the app, comme la diffusion en direct, 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 (LLM), 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.

Cet article explore les excursions dans le temps et leurs implications.

Télécharger PDF: