🛰️ Daily AI Frontier
‹ back to 2026-09-10

JarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task Composition

arXiv cs.AI LLM Agents Zixiang Chen, Yuheng Lu, Zihao Cheng, Zeming Liu, Jizeng Bai, Ziye Huang, Zhiyin Lin, Zihan Li, Yuhang Guo, Yunhong Wang, Haifeng Wang 2026-09-09
Representative image for JarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task Composition

TL;DR - JarvisGUI is a dynamic benchmark for evaluating GUI agents on workflows spanning Android, Windows, and Ubuntu. It exposes major gaps in agents’ ability to transfer state, reason across platforms, and manage long-horizon dependencies.

  • Models tasks as typed input-output transformations, enabling automatic composition of multi-step cross-device workflows.
  • Evaluates coordinated agent interactions in virtual environments across three operating systems.
  • Addresses limitations of existing benchmarks that focus on static, single-device tasks.
  • Finds that state-of-the-art open-source GUI agents struggle with cross-device coordination requirements.

view merged work →