MementoGUI-Bench
MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents
Ziyun Zeng, Hang Hua, Bocheng Zou, Mu Cai, Rogerio Feris, Jiebo Luo · 2026-05-18
- Modality
- GUI & computer use
- Data
- Real data
- Task · ground truth
- Act./Learn · Reg.+Act.
- Scope
- Memory-specific benchmark
What it tests
- CECross-modal evidenceDirectly evaluated
- LELong-range evidenceDirectly evaluated
- SCState changesPartially evaluated
- CFConflicting memoriesNot evaluated
- UQUnanswerable queriesNot evaluated
- MAMemory-grounded actionDirectly evaluated
- GSPersistent interface stateDirectly evaluated
- AOAction–outcome associationDirectly evaluated
- XRCross-session reuseDirectly evaluated
Survey notes
Held-out GUI trajectories require historical constraints and subgoals, with memory-consistency scoring and an episodic bank.