List your company

Mobile GUI Agent Navigation on MobileWorld

58Success Rate (SR)Task-State Representation (Kimi-k2.5)
42.446.4550.554.55Jul 1, 2026

Evaluation results

MethodLinks
Task-State Representation (Kimi-k2.5)Base Model=Kimi-k2.5, Context=Proposed2026.075828.39
Task-State Representation (Qwen3.5-plus)Base Model=Qwen3.5-plus, Context=Proposed2026.07552712
Kimi-k2.5Context=Baseline2026.074929.6—
Qwen3.5-plusContext=Baseline2026.074325.1—