List your company

E-commerce Pricing Decision Alignment on E-commerce Pricing Expert Trajectories (Offline Evaluation)

2.836Avg. Q-ScoreAIGP
2.345122.472562.62.72744Jun 25, 2026

Evaluation results

MethodLinks
AIGPalignment_stage=SFT+DPO2026.062.8360.06282.5111.8311.86
AIGPalignment_stage=DPO-only2026.062.7940.06779.2611.8111.84
RL-DT2026.062.6940.07873.8911.6511.71
AIGPmode=FullSeq2026.062.5910.08271.3211.7311.78
Qwen3-30B-A3B2026.062.5850.08569.2211.7411.8
Price-Sales2026.062.5640.08471.0811.6211.68
Qwen3-235B-A22B2026.062.5560.08967.0711.6911.76
AIGPalignment_stage=SFT-only2026.062.5540.08668.9811.7111.77
RL-SAC2026.062.4940.09763.9511.5211.57
RL-DDPG2026.062.3640.1156.9111.4111.47