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

arXiv:2601.18491v2 Announce Type: replace 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.

Related

• ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis
• STARS: Skill-Triggered Audit for Request-Conditioned Invocation Safety in Agent Systems
• A Benchmark for Evaluating Outcome-Driven Constraint Violations in Autonomous AI Agents
• SafeHarness: Lifecycle-Integrated Security Architecture for LLM-based Agent Deployment
• SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills

Source: arXiv cs.AI | 2026-04-24