File size: 661 Bytes
18ae114 8e05260 |
1 2 3 4 5 6 7 8 9 10 11 12 |
---
license: apache-2.0
---
TS-Guard is a guardrail model for step-level tool invocation safety detection. TS-Guard is trained via reinforcement learning with a multi-task reward scheme tailored for agent security, enabling identifying harmful user requests and attack vectors in agent-environment interaction logs, detecting unsafe tool invocation before execution, and providing interpretable analysis and reasoning process
|