List your company

Reward Performance on Car Negotiation High-data

41.42Test-Time RewardMC
31.90434.374536.84539.3155May 23, 2026

Evaluation results

MethodLinks
MCtraining_regime=BOOST2026.0541.42
MCtraining_regime=Bilevel Only2026.0541.31
ILQLtraining_regime=Bilevel Only2026.0537.55
ILQLtraining_regime=BOOST2026.0537.36
ILQLtraining_regime=Vanilla2026.0535.33
MCtraining_regime=Vanilla+Syn2026.0535.09
ILQLtraining_regime=Vanilla+Syn2026.0533
MCtraining_regime=Vanilla2026.0532.27