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

Failure prediction on tau2-bench Within corpus

0.719ROC AUC

R-GCN

0.688840.696670.70450.71233Jun 22, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
0.719
2026.06
0.709
2026.06
0.694
2026.06
0.69