Research

Paper

AI LLM March 25, 2026

Environment-Grounded Multi-Agent Workflow for Autonomous Penetration Testing

Authors

Michael Somma, Markus Großpointner, Paul Zabalegui, Eppu Heilimo, Branka Stojanović

Abstract

The increasing complexity and interconnectivity of digital infrastructures make scalable and reliable security assessment methods essential. Robotic systems represent a particularly important class of operational technology, as modern robots are highly networked cyber-physical systems deployed in domains such as industrial automation, logistics, and autonomous services. This paper explores the use of large language models for automated penetration testing in robotic environments. We propose an environment-grounded multi-agent architecture tailored to Robotics-based systems. The approach dynamically constructs a shared graph-based memory during execution that captures the observable system state, including network topology, communication channels, vulnerabilities, and attempted exploits. This enables structured automation while maintaining traceability and effective context management throughout the testing process. Evaluated across multiple iterations within a specialized robotics Capture-the-Flag scenario (ROS/ROS2), the system demonstrated high reliability, successfully completing the challenge in 100\% of test runs (n=5). This performance significantly exceeds literature benchmarks while maintaining the traceability and human oversight required by frameworks like the EU AI Act.

Metadata

arXiv ID: 2603.24221
Provider: ARXIV
Primary Category: cs.RO
Published: 2026-03-25
Fetched: 2026-03-26 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.24221v1</id>\n    <title>Environment-Grounded Multi-Agent Workflow for Autonomous Penetration Testing</title>\n    <updated>2026-03-25T11:50:08Z</updated>\n    <link href='https://arxiv.org/abs/2603.24221v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.24221v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>The increasing complexity and interconnectivity of digital infrastructures make scalable and reliable security assessment methods essential. Robotic systems represent a particularly important class of operational technology, as modern robots are highly networked cyber-physical systems deployed in domains such as industrial automation, logistics, and autonomous services. This paper explores the use of large language models for automated penetration testing in robotic environments. We propose an environment-grounded multi-agent architecture tailored to Robotics-based systems. The approach dynamically constructs a shared graph-based memory during execution that captures the observable system state, including network topology, communication channels, vulnerabilities, and attempted exploits. This enables structured automation while maintaining traceability and effective context management throughout the testing process. Evaluated across multiple iterations within a specialized robotics Capture-the-Flag scenario (ROS/ROS2), the system demonstrated high reliability, successfully completing the challenge in 100\\% of test runs (n=5). This performance significantly exceeds literature benchmarks while maintaining the traceability and human oversight required by frameworks like the EU AI Act.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.RO'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-25T11:50:08Z</published>\n    <arxiv:primary_category term='cs.RO'/>\n    <author>\n      <name>Michael Somma</name>\n    </author>\n    <author>\n      <name>Markus Großpointner</name>\n    </author>\n    <author>\n      <name>Paul Zabalegui</name>\n    </author>\n    <author>\n      <name>Eppu Heilimo</name>\n    </author>\n    <author>\n      <name>Branka Stojanović</name>\n    </author>\n  </entry>"
}