Paper Detail

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

Zixiang Chen, Yuheng Lu, Zihao Cheng, Zeming Liu, Jizeng Bai, Ziye Huang, Zhiyin Lin, Zihan Li, Yuhang Guo, Yunhong Wang, Haifeng Wang

arxiv Score 15.2

Published 2026-09-09 · First seen 2026-09-10

Research Track B · General AI

Abstract

Real-world GUI usage frequently involves workflows that span multiple devices and platforms, requiring the transfer of intermediate results, maintenance of shared state, and coordination across heterogeneous environments. However, existing GUI benchmarks overwhelmingly evaluate agents on single-device, statically defined tasks, thus leaving such cross-device capabilities largely unexamined, resulting in an overly optimistic assessment of agents' readiness for real-world usage. We introduce JarvisGUI, a dynamic benchmark that evaluates GUI agents on cross-device workflows requiring coordinated interaction across heterogeneous platforms, including Android, Windows, and Ubuntu. Specifically, JarvisGUI formulates GUI tasks as input-output transformations under a lightweight type system, which allows us to automatically compose multi-step, cross-device workflows and dynamically evaluate agent performance within a unified framework. By evaluating agents in virtual environments spanning multiple operating systems, JarvisGUI reveals that state-of-the-art open-source GUI agents struggle with the state-transfer awareness, cross-platform contextual reasoning, and long-horizon dependency management required for real-world workflows, exposing a critical capability gap invisible to existing benchmarks.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{chen2026jarvisgui,
  title = {JarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task Composition},
  author = {Zixiang Chen and Yuheng Lu and Zihao Cheng and Zeming Liu and Jizeng Bai and Ziye Huang and Zhiyin Lin and Zihan Li and Yuhang Guo and Yunhong Wang and Haifeng Wang},
  year = {2026},
  abstract = {Real-world GUI usage frequently involves workflows that span multiple devices and platforms, requiring the transfer of intermediate results, maintenance of shared state, and coordination across heterogeneous environments. However, existing GUI benchmarks overwhelmingly evaluate agents on single-device, statically defined tasks, thus leaving such cross-device capabilities largely unexamined, resulting in an overly optimistic assessment of agents' readiness for real-world usage. We introduce Jarvi},
  url = {https://arxiv.org/abs/2609.10451},
  keywords = {cs.AI},
  eprint = {2609.10451},
  archiveprefix = {arXiv},
}

Metadata

{}