Article

Coverage and Complementarity of Three Agentic AI Risk Taxonomies Across 131 Real World Incidents

2026-08-21

Abstract excerpt

<title>Abstract</title> <p>The transition from generative AI to agentic AI has produced a rapid proliferation of failure taxonomies. Three now dominate: the OWASP Top 10 for Agentic Applications 2026 (OWASP-ASI), the Microsoft AI Red Team taxonomy of failure modes in agentic AI systems (MSFT-AIRT), and the NIST AI Risk Management Framework (NIST AI RMF). Practitioners, regulators, and researchers choosing among t...

Topics

Open a Topic to create a Post that cites this publication.

Uncategorized literature

Identifiers and source

Literature Corpus work: 7be991bd-e542-5558-a5bb-12908a1dac74
DOI: 10.21203/rs.3.rs-10425736/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Coverage and Complementarity of Three Agentic AI Risk Taxonomies Across 131 Real World IncidentsDOI 10.21203/rs.3.rs-10425736/v1Read

Trustworthy Agentic AI: A Rapid, PRISMA-Informed Evidence Review of Safety, Explainability, Alignment, and Human Oversight in Autonomous AI SystemsSemantic proximity Read

A Concern-Oriented Governance Approach for Securing Agentic AISemantic proximity Read

Safety, Hallucination, and Failure Modes in Agentic Health AI: A State-of-the-Art ReviewSemantic proximity Read

Balancing autonomy and oversight in reliable agentic artificial intelligence through adaptive human interaction architecturesSemantic proximity Read

Agentic AI: A Review, Applications, and Open Research ChallengesSemantic proximity Read

SORT-AI: Domain Architecture and Structural Diagnostics for Advanced AI SystemsSemantic proximity Read

The Technical–Regulatory Correspondence Matrix: A Practical Development Framework for Building GDPR- and AI Act-Compliant High-Risk AI SystemsSemantic proximity Read

Decision Support or High-Risk? Classifying AI Workforce-Intelligence Systems Under the EU AI ActSemantic proximity Read

Artificial eXperience Intelligence (AXI): An Engineering Discipline for the Human Experience of AI SystemsSemantic proximity Read

The Moral Compass as a Design Constraint: Ergonomic Principles for Building Safe AGISemantic proximity Read

A deterministic safety pipeline for therapeutic AI in elderly assisted livingSemantic proximity Read

Detection and Mitigation of Mythos-Class Frontier Model Capabilities: A Layered Reference ArchitectureSemantic proximity Read