List your company

Web/tool tasks on WebShop 1000 (test)

81.2Success RateCVT-RL
73.71275.65677.679.544Jun 3, 2026

Evaluation results

MethodLinks
CVT-RLDescription=per-seed CVT-RL success, Split (train/dev/test)=6800/900/1000, Individual Seeds=80.8/81.9/82.4/80.7/80.22026.0681.23.5
IMDescription=information-matched counterfactual-process RL, Split (train/dev/test)=6800/900/10002026.0677.7—
CMDescription=compute-matched non-causal RL, Split (train/dev/test)=6800/900/10002026.0674—