Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Language Agent Task on WebShop (OOD)

49.6Score

Task-Perturbed NLL Optimization

45.02446.21247.448.588Jun 25, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
49.6
2026.06
47.5
2026.06
47.1
2026.06
45.2