List your company

E-commerce Price Optimization on Tao Factory Online A/B Test 14-Day Horizon

8.2MARAIGP
0.58722.56364.546.5164Jun 25, 2026

Evaluation results

MethodLinks
AIGPMode=SFT+DPO2026.068.213.217.59
Qwen3-235B-A22BBackbone=Qwen3-235B-A22B2026.067.3710.56.62
AIGPMode=SFT-only2026.063.347.855.29
Qwen3-30B-A3BBackbone=Qwen3-30B-A3B2026.062.984.894.33
RL-DT2026.060.889.043.46