#artificial intelligence
Sep 2026
ActGov: Governing LLM Agent Actions via Policy-Constrained Validation
It is demonstrated that ActGov can enforce fine-grained authorization over dynamic agent executions without relying on the underlying LLM to correctly identify malicious instructions, significantly outperforming existing defenses.
Kai-Yuan Zhang, Yu-Ke Peng, Ke Jiang et al.
· arXiv.org · 1 citation
· ⚡1