step-level-detection

Here is 1 public repository matching this topic...

glo26 / stepshield

StepShield: When, Not Whether to Intervene on Rogue Agents — NeurIPS 2026 benchmark for temporal evaluation of AI agent guardrails (9,429 trajectories, step-level annotations)

benchmark dataset ai-safety guardrails agent-security neurips-2026 step-level-detection

Updated Sep 5, 2026
Python

Add this topic to your repo

To associate your repository with the step-level-detection topic, visit your repo's landing page and select "manage topics."

Learn more