AgentCyTE: Leveraging Agentic AI to Generate Cybersecurity Training & Experimentation Scenarios

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rodriguez, Ana M., Acosta, Jaime, Kotal, Anantaa, Piplai, Aritran
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917049240911872
author Rodriguez, Ana M.
Acosta, Jaime
Kotal, Anantaa
Piplai, Aritran
author_facet Rodriguez, Ana M.
Acosta, Jaime
Kotal, Anantaa
Piplai, Aritran
contents Designing realistic and adaptive networked threat scenarios remains a core challenge in cybersecurity research and training, still requiring substantial manual effort. While large language models (LLMs) show promise for automated synthesis, unconstrained generation often yields configurations that fail validation or execution. We present AgentCyTE, a framework integrating LLM-based reasoning with deterministic, schema-constrained network emulation to generate and refine executable threat environments. Through an agentic feedback loop, AgentCyTE observes scenario outcomes, validates correctness, and iteratively enhances realism and consistency. This hybrid approach preserves LLM flexibility while enforcing structural validity, enabling scalable, data-driven experimentation and reliable scenario generation for threat modeling and adaptive cybersecurity training. Our framework can be accessed at: https://github.com/AnantaaKotal/AgentCyTE
format Preprint
id arxiv_https___arxiv_org_abs_2510_25189
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AgentCyTE: Leveraging Agentic AI to Generate Cybersecurity Training & Experimentation Scenarios
Rodriguez, Ana M.
Acosta, Jaime
Kotal, Anantaa
Piplai, Aritran
Cryptography and Security
Designing realistic and adaptive networked threat scenarios remains a core challenge in cybersecurity research and training, still requiring substantial manual effort. While large language models (LLMs) show promise for automated synthesis, unconstrained generation often yields configurations that fail validation or execution. We present AgentCyTE, a framework integrating LLM-based reasoning with deterministic, schema-constrained network emulation to generate and refine executable threat environments. Through an agentic feedback loop, AgentCyTE observes scenario outcomes, validates correctness, and iteratively enhances realism and consistency. This hybrid approach preserves LLM flexibility while enforcing structural validity, enabling scalable, data-driven experimentation and reliable scenario generation for threat modeling and adaptive cybersecurity training. Our framework can be accessed at: https://github.com/AnantaaKotal/AgentCyTE
title AgentCyTE: Leveraging Agentic AI to Generate Cybersecurity Training & Experimentation Scenarios
topic Cryptography and Security
url https://arxiv.org/abs/2510.25189