List your company

Reward Performance on Webshop Agent Low-data

0.4Test-Time RewardMC
0.22320.26910.3150.3609May 23, 2026

Evaluation results

MethodLinks
MCtraining_regime=BOOST2026.050.4
ILQLtraining_regime=BOOST2026.050.38
MCtraining_regime=Bilevel Only2026.050.32
ILQLtraining_regime=Bilevel Only2026.050.32
ILQLtraining_regime=Vanilla2026.050.3
ILQLtraining_regime=Vanilla+Syn2026.050.27
MCtraining_regime=Vanilla2026.050.24
MCtraining_regime=Vanilla+Syn2026.050.23