Tool-use Policy Auditing on τ2-BENCH Retail (base)
59.6PASS^4Baseline
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| BaselineAgent and Verifier Model=GPT 5.4, n=4, Verifier type=paired-verifier2026.06 | 59.6 | 85.7 | 57.9 | |
| PG-CHECKLISTVariant=CHECKLIST, Agent and Verifier Model=GPT 5.4, n=4, Verifier type=paired-verifier2026.06 | 36 | 85.7 | 32.7 | |
| PG-RAWVariant=RAW, Agent and Verifier Model=GPT 5.4, n=4, Verifier type=paired-verifier2026.06 | 17.5 | 85.7 | 13.1 |