ToolEmu

Evals

Benchmark / dataset

LM-emulated sandbox to find risky agent tool actions.

Category
Agent safety & harmful actions
Insurance exposure
Agent actions
Publisher
Univ. of Toronto / Vector
Publisher type
Academic
License
Apache-2.0
Status
Stale (>12mo)
Last commit
2024-03-22
Stars
226

View source on GitHub →

Wanich Risk Lab, 2026.