Meta FAIR Launches AI Agent Safety Benchmark
Meta's FAIR lab releases a comprehensive new benchmark framework designed to evaluate the safety of autonomous AI agents…
🏷️ Agent Safety
5 articles about 'Agent Safety'
RSAC 2026 Wraps Up: AI Agents Emerge as the Biggest Cybersecurity Focal Point
RSAC 2026 has concluded, with AI agents taking center stage as the core topic of the conference. They represent both a p…
U.S. and Allies Issue Joint Guidelines for Secure Deployment of AI Agents
The U.S. government, in coordination with multiple allied nations, has released a guidance document on the secure deploy…
Decoupled Human-in-the-Loop Systems: Making AI Agents Safer and More Controllable
A latest arXiv paper proposes a decoupled Human-in-the-Loop (HITL) system architecture that separates human oversight me…
The Rise of AI Agent Ecosystems: The Internet Is Entering an Era of Fog
Import AI Issue 443 offers an in-depth exploration of Moltbook, agent ecosystems, and the transformation of the internet…
1