List your company

GUI Agent Task Completion on WeChat Mini-App Real-World (test)

42.28Success Rate (Human)code-native-reward (Ours)
36.695238.145139.59541.0449Feb 15, 2026

Evaluation results

MethodLinks
code-native-reward (Ours)Training Environment=Synthetic Environment, Hours per step=0.1013, Cost per step=$02026.0242.28
VLM-reward (Ours)Training Environment=Synthetic Environment, Hours per step=0.1036, Cost per step=$0.52026.0241.61
VLM-rewardTraining Environment=Real-World Environment, Hours per step=0.2272, Cost per step=$2402026.0240.94
Base ModelTraining Environment=N/A2026.0236.91