Agentic-ZTA: A Multi-Agent Architecture for Autonomous Zero Trust Enforcement
On the map: LLM agents and tool use → Agent threats, guardrails and governance
Abstract (arXiv)
Agentic AI is emerging as a promising paradigm for automating complex cybersecurity decisions, yet its use in enforcing zero trust introduces significant challenges in safety, reliability, and policy compliance. This paper presents Agentic AI based zero trust architecture (Agentic-ZTA) that operationalizes the NIST SP 800-207 ZTA architecture control loop through coordinated multi- agent decision pipeline. In the proposed framework, policy knowledge is embedded into a retrieval-augmented generation pipeline and retrieved at inference time as top-k relevant policies. Access requests are intercepted by the Policy Enforcement Point (PEP), enriched with contextual metadata. The request context is routed to a policy engine agent which invokes domain-specialized core agents first followed by supporting agents, if further evaluation needed. AI agents reason over access context, policy constraints and determine trust. The retrieved policies are embedded into agent prompt during inference time and agentic trust scores are aggregated and evaluated by a trust-algorithm, producing the final access decision for enforcement under continuous verification. We implement Agentic-ZTA in a testbed and evaluate it on representative access-control use cases scenarios. Our Agentic-ZTA framework achieves 95.0% accuracy, 93.9% precision, and 96.3% recall, and demonstrate the feasibility of enforcing zero trust using AI agents.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 14 of its 58 references that are in the map. First posted on arXiv 5 Oct 2026.
Builds on
14 of 58 references.
References · 14
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
- 2023A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Uglycited by 387
- 2024AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathwayscited by 127
- 2024Limitations of the LLM-as-a-Judge Approach for Evaluating LLM Outputs in Expert Knowledge Taskscited by 106
- 2022The Role of Machine Learning in Cybersecuritycited by 22
- 2023Learning Near-Optimal Intrusion Responses Against Dynamic Attackerscited by 15
- 2024SECURE: Benchmarking Large Language Models for Cybersecuritycited by 14
- 2025Say What You Mean: Natural Language Access Control with Large Language Models for Internet of Thingscited by 6
- 2022Toward Deep Learning Based Access Controlcited by 4
- 2021Adaptive ABAC Policy Learning: A Reinforcement Learning Approachcited by 3
- 2025Interpretable Anomaly-Based DDoS Detection in AI-RAN with XAI and LLMscited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Trustworthy Agentic AI: A Comprehensive Cybersecurity and Systems Survey on Threat Landscapes, Defense Architectures, and Open Challenges
- 2026When Agents Control Robots: A Zero Trust Policy Model for Agentic Cyber-Physical Systems
- 2026Hybrid Inspection and Task-Based Access Control in Zero-Trust Agentic AI
- 2025Adaptive Cybersecurity Architecture for Digital Product Ecosystems Using Agentic AI
- 2025Fortifying the Agentic Web: A Unified Zero-Trust Architecture Against Logic-layer Threats
- 2025A Novel Zero-Trust Identity Framework for Agentic AI: Decentralized Authentication and Fine-Grained Access Control
- 2025The Evolution of Agentic AI in Cybersecurity: From Single LLM Reasoners to Multi-Agent Systems and Autonomous Pipelines
- 2025Using the NANDA Index Architecture in Practice: An Enterprise Perspective