List your company

Mobile GUI Agent Navigation on MemGUI-Bench

42.97Success RateTask-State Representation (Kimi-k2.5)
25.903630.334334.76539.1957Jul 1, 2026

Evaluation results

MethodLinks
Task-State Representation (Kimi-k2.5)Base Model=Kimi-k2.5, Context=Proposed2026.0742.9755.80.78
Kimi-k2.5Context=Baseline2026.0742.1951.6—
Task-State Representation (Qwen3.5-plus)Base Model=Qwen3.5-plus, Context=Proposed2026.0728.9159.82.35
Qwen3.5-plusContext=Baseline2026.0726.5660.5—