Your AI Agent Has More Permissions Than Your Intern. And No One Gave It a Contract.
Why delegating full identity to AI agents is a time bomb, and a five-layer architecture to defuse it before the first incident.
Tag
Agentic AI
7 articles tagged with this topic.
Beyond Static Evaluation: Building Simulation Environments for Scalable Agentic Reinforcement Learning
A new arXiv paper proposes AgenticAI-Supervisor, a simulation environment that decouples environment creation from scalable execution for verifiable agentic RL.
Expanding Managed Agents in Gemini API: Background Tasks, Remote MCP and More
Google's July 2026 Managed Agents update adds background execution, remote MCP integration, and credential refresh. Each new capability expands the attack surface. Here is what security teams need to know.
Information Gain-based Rollout Policy Optimization: Adaptive Tree-Structured Rollouts for Multi-Turn LLM Agents
IGRPO treats intermediate-state informativeness as the organizing principle of rollout collection, unifying tree-structured exploration with policy learning.
Shadow AI and the New Problem of Delegated Authority
A research briefing on the shift from unmanaged AI usage to agentic systems with delegated authority, and the controls needed to govern both risk domains.
MCP Security: When Protocol Becomes Attack Vector
Agentjacking demonstrated that MCP trust is not automatic. Here is how the attack works, why protocol-level security matters, and what controls need to change.
The AI Agent Security Landscape — June 2026
June produced at least four coordinated vulnerability disclosures affecting every major AI coding agent. The pattern is structural.