List your company

Reward Performance on Car Negotiation Low-data

40.92Test-Time RewardMC
25.340829.385433.4337.4746May 23, 2026

Evaluation results

MethodLinks
MCtraining_regime=BOOST2026.0540.92
MCtraining_regime=Bilevel Only2026.0536.28
ILQLtraining_regime=BOOST2026.0534.91
MCtraining_regime=Vanilla+Syn2026.0531.08
ILQLtraining_regime=Bilevel Only2026.0529.08
ILQLtraining_regime=Vanilla2026.0527.22
MCtraining_regime=Vanilla2026.0526.73
ILQLtraining_regime=Vanilla+Syn2026.0525.94