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

ALFWorld Task Success on ALFWorld Noisy (T=100)

97Task Success Count

TraceRetain-CEM

87.6490.0792.594.93Jun 28, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.06
979,299
2026.06
969,098
2026.06
958,998
2026.06
948,897
2026.06
888,093