Tool-use Policy Auditing on τ2-BENCH Telecom base
20.2PASS^4
PG-CHECKLIST
Updated 26d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.06 | 20.2 | 10.2 | 53.8 | |
2026.06 | 19.3 | 9.1 | 53.8 | |
2026.06 | 14.9 | 6.8 | 42.3 |
PG-CHECKLIST
| Method | Links | |||
|---|---|---|---|---|
2026.06 | 20.2 | 10.2 | 53.8 | |
2026.06 | 19.3 | 9.1 | 53.8 | |
2026.06 | 14.9 | 6.8 | 42.3 |