DataScope
What Memory Do GUI Agents Really Need? From Passive Records to Active Task-Driving States
Chen Liu, Ling Chen, Hanzhang Zhou, Xu Zhang, Quyu Kong, Panrong Tong, et al. · 2026-07-02
- Modality
- GUI & computer use
- Data
- Hybrid (real + synthetic/simulated)
- Task · ground truth
- Act. · State
- Scope
- Memory-specific benchmark
What it tests
- CECross-modal evidencePartially evaluated
- LELong-range evidenceDirectly evaluated
- SCState changesDirectly evaluated
- CFConflicting memoriesNot evaluated
- UQUnanswerable queriesNot evaluated
- MAMemory-grounded actionDirectly evaluated
- GSPersistent interface stateDirectly evaluated
- AOAction–outcome associationDirectly evaluated
- XRCross-session reuseNot evaluated
Survey notes
Cross-page and cross-app workflows require retaining targets and operation status; resulting app states verify progress and scope.