JarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task Composition
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
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 87%NirDiamant/GenAI_Agents →
“Fuzzy title match (0.94): “JarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task” ≈ “NirDiamant/GenAI_Agents””
- FuzzySimilar title/name (fuzzy) · 84%Unity-Technologies/ml-agents →
“Fuzzy title match (0.92): “JarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task” ≈ “Unity-Technologies/ml-agents””
- FuzzySimilar title/name (fuzzy) · 66%NirDiamant/agents-towards-production →
“Fuzzy title match (0.78): “JarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task” ≈ “NirDiamant/agents-towards-production””
- FuzzyOverlapping authors or contributors · 62%ray-project/ray →
“Shared author/contributor keys: wang”
- FuzzyOverlapping authors or contributors · 62%Zeyi-Lin/HivisionIDPhotos →
“Shared author/contributor keys: lin”
- LinkedLinked via arxiv author · 85%Zixiang Chen →
“JarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task Composition”
- LinkedLinked via arxiv author · 85%Yuheng Lu →
“JarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task Composition”
- LinkedLinked via arxiv author · 85%Zihao Cheng →
“JarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task Composition”