Agentic Security: A Systematization of Tools, Failure Modes, and Design Laws for LLM-Driven Penetration Testing
Source
arxiv.org
Author
Israt Moyeen Noumi, Tarannum Ahmed Nowshin, Md. Mehedi Hasan Nipu, Mohammad Sakib Mahmood, Md. Jakir Hossain, M. F. Mridha
Date
Why it matters
Long-lived AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → sessions shed resident evidence as phase count grows while short-lived sub-agents extend the usable horizon — a concrete argument for how to shard sessions in any tool-heavy agent.
Terms in this piece · Glossary
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
articleWhen Passing Tests Hides Vulnerabilities: An Empirical Study of Silent Failures in Agentic SystemsWenji Bai, Muhammad Waseem, Zeeshan Rasheed, Jaakko Peltonen, Pekka Abrahamsson
articleATLAS: Discovering Agent Strategies through LLM-Guided Abstraction and Automata LearningIgnacio D. Lopez-Miguel, Andreas Happe, J\"urgen Cito, Ezio Bartocci, Bettina K\"onighofer, Martin Tappler
articleSupporting Industrial Test-Failure Analysis with LLM-Based Systems: An Experience ReportEric Jansson, Per Strandberg, Thomas S\"orensen, Eduard Paul Enoiu, Wasif Afzal