GUI Memory
41 systems and 7 benchmarks whose primary modality is GUI & computer-use.
How they represent memory
How T2 systems change it
Representation × management tier
T1 Static Memory 13 · 32% T2 Dynamic Memory 25 · 61% T3 Self-Evolving Memory 3 · 7% Total
Each system counted once, at its highest tier. Circle area shows the value. Hover to compare with chance; click to list the systems.
What its benchmarks test
- Cross-modal evidenceCE2
- Long-range evidenceLE7
- State changesSC5
- Conflicting memoriesCF0
- Unanswerable queriesUQ1
- Memory-grounded actionMA7
- Persistent interface stateGS6
- Action–outcome associationAO5
- Cross-session reuseXR4
All 41 systems
- ActionEngineT2 · 2026
- Adaptive Workflow AgentsT2 · 2026
- AGMemT1 · 2026
- ATMemT2 · 2026
- AutoMMemoT2 · 2026
- Darwinian MemoryT2 · 2026
- EAMT1 · 2026
- GraphPilotT1 · 2026
- HyMEMT2 · 2026
- KnowAct-GUIClawT3 · 2026
- MAGNETT2 · 2026
- Mem-WT2 · 2026
- MementoGUIT2 · 2026
- OCR-MemoryT2 · 2026
- SE-GAT2 · 2026
- SKILL.nbT3 · 2026
- STAMPT2 · 2026
- TGL Proactive Trigger and RoutingT2 · 2026
- UI-KOBET2 · 2026
- UI-MemT1 · 2026
- UI-VoyagerT1 · 2026
- Auto-scaling Continuous MemoryT1 · 2025
- Chain-of-MemoryT2 · 2025
- GUI-explorerT1 · 2025
- LiteWebAgentT1 · 2025
- MGAT2 · 2025
- Mirage-1T2 · 2025
- MIRIXT2 · 2025
- Mobile-Agent-ET2 · 2025
- Mobile-Agent-VT1 · 2025
- MobileUseT2 · 2025
- MobiMemT3 · 2025
- OdysseyAgentT1 · 2025
- PAL-UIT2 · 2025
- UI-TARST2 · 2025
- Agent ST2 · 2024
- AppAgent v2T1 · 2024
- AutoDroidT1 · 2024
- Mobile-Agent-v2T2 · 2024
- MobileGPTT2 · 2024
- AppAgentT1 · 2023