# Agentic-ZTA: A Multi-Agent Architecture for Autonomous Zero Trust Enforcement

arXiv: https://arxiv.org/abs/2610.05782 · HTML: https://mlsanity.com/paper/2610.05782/

## 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.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 14 of 14)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly](https://mlsanity.com/paper/2312.02003/) (2023)
- [AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways](https://mlsanity.com/paper/2406.02630/) (2024)
- [Limitations of the LLM-as-a-Judge Approach for Evaluating LLM Outputs in Expert Knowledge Tasks](https://mlsanity.com/paper/2410.20266/) (2024)
- [The Role of Machine Learning in Cybersecurity](https://mlsanity.com/paper/2206.09707/) (2022)
- [Learning Near-Optimal Intrusion Responses Against Dynamic Attackers](https://mlsanity.com/paper/2301.06085/) (2023)
- [SECURE: Benchmarking Large Language Models for Cybersecurity](https://mlsanity.com/paper/2405.20441/) (2024)
- [Say What You Mean: Natural Language Access Control with Large Language Models for Internet of Things](https://mlsanity.com/paper/2505.23835/) (2025)
- [Toward Deep Learning Based Access Control](https://mlsanity.com/paper/2203.15124/) (2022)
- [Adaptive ABAC Policy Learning: A Reinforcement Learning Approach](https://mlsanity.com/paper/2105.08587/) (2021)
- [Interpretable Anomaly-Based DDoS Detection in AI-RAN with XAI and LLMs](https://mlsanity.com/paper/2507.21193/) (2025)
- [ZT-SDN: An ML-powered Zero-Trust Architecture for Software-Defined Networks](https://mlsanity.com/paper/2411.15020/) (2024)
- [LLMAC: A Global and Explainable Access Control Framework with Large Language Model](https://mlsanity.com/paper/2602.09392/) (2026)

## 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.