AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security

TL;DR

AgentDoG introduces a hierarchical taxonomy, a new safety benchmark, and a diagnostic framework for improving AI agent safety, transparency, and root cause analysis in complex scenarios.

Contribution

It presents a novel agentic risk taxonomy, a fine-grained safety benchmark, and a diagnostic guardrail framework with open-source models for enhanced AI safety.

Findings

AgentDoG achieves state-of-the-art safety moderation performance.

Models and datasets are openly released for community use.

The framework enables root cause diagnosis of unsafe actions.

Abstract

The rise of AI agents introduces complex safety and security challenges arising from autonomous tool use and environmental interactions. Current guardrail models lack agentic risk awareness and transparency in risk diagnosis. To introduce an agentic guardrail that covers complex and numerous risky behaviors, we first propose a unified three-dimensional taxonomy that orthogonally categorizes agentic risks by their source (where), failure mode (how), and consequence (what). Guided by this structured and hierarchical taxonomy, we introduce a new fine-grained agentic safety benchmark (ATBench) and a Diagnostic Guardrail framework for agent safety and security (AgentDoG). AgentDoG provides fine-grained and contextual monitoring across agent trajectories. More Crucially, AgentDoG can diagnose the root causes of unsafe actions and seemingly safe but unreasonable actions, offering provenance and transparency beyond binary labels to facilitate effective agent alignment. AgentDoG variants are available in three sizes (4B, 7B, and 8B parameters) across Qwen and Llama model families. Extensive experimental results demonstrate that AgentDoG achieves state-of-the-art performance in agentic safety moderation in diverse and complex interactive scenarios. All models and datasets are openly released.