AgentDojo-Traj
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Step-level tool invocation safety detection | AgentDojo-Traj | Accuracy91.72 | 20 |
Showing 1 of 1 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Step-level tool invocation safety detection | AgentDojo-Traj | Accuracy91.72 | 20 |