Newest papers

LiveUIBench: Evaluating Agent as App Workflows

Tong Zhang, Yuxuan Cheng, Ruimin Zhang, Yun Peng, Tao Xie · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.27977 · cited by 0 works (OpenAlex) · open-access PDF

Arabic

يمكن للمستخدمين أن يقدموا ميزات مناسبة لتنفيذ المهام اليومية. ومع ذلك، قد يكون لديهم مستخدمين مختلفين أو حتى متناقضين متطلبات للتطبيق نفسه، في حين قد تتغير متطلبات المستخدم نفسه مع مرور الوقت. قد يلزم تطوير التطبيقات التي تم إنشاؤها من خلال اتجاهات agent-to-app أو UI-to-code التغييرات في التطبيق الذي تم إنشاؤه. ونحن نقدم Agent as App، وظيفة التي تؤكد مستخدميها متطلباتهم باللغة الطبيعية، وتقوم بمراجعة التطبيق الشخصي في الوقت الذي تستخدمه. ونحن نستخدم LiveUIAgent، الذي يوفر أساسًا صغيرًا لعملية التخصيص كما يتطور المتطلبات. ونقدم LiveUIBench، علامة

Machine translation (Meta M2M100); the English original follows.

Abstract

Applications provide convenient features for users to complete daily tasks. However, different users may have different or even conflicting requirements for the same application, while the requirements of the same user may change over time. Personalizing applications produced by agent-to-app or UI-to-code approaches can require changes to the generated implementation. We propose Agent as App, a task in which users express their requirements in natural language and an agent creates a personalized application while continuing to supply its behavior during use. We implement LiveUIAgent, which generates a task-specific orchestration connecting the user interface, saved information, and service actions. A shared agent runtime renders and updates the interface while carrying out the requested operations. Revising the orchestration and interface while reusing that runtime provides a lightweight basis for personalization as requirements evolve. We introduce LiveUIBench, a benchmark with diverse requirements and ordered interactions across personal services. The empirical findings show that the evaluated models struggle to complete these workflows reliably. Applications can satisfy many local checks while leaving the overall task unfinished, and greater partial coverage can coincide with fewer completed workflows.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Orchestration, Workflow, Personalization, Task (project management), Reuse

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange