---
title: "RedTeamLLM: an Agentic AI framework for offensive security (arXiv:2505.06913) | Papers With Code Cyber"
description: "From automated intrusion testing to discovery of zero-day attacks before software launch, agentic AI calls for great promises in security engineering. This strong…"
canonical: "https://paperswithcode-cyber.com/paper/2505.06913"
type: "paper"
---

# RedTeamLLM: an Agentic AI framework for offensive security

arXiv:2505\.06913 · 2025-05-11

Authors: Brian Challita, Pierre Parrend

## Abstract

From automated intrusion testing to discovery of zero\-day attacks before software launch, agentic AI calls for great promises in security engineering\. This strong capability is bound with a similar threat: the security and research community must build up its models before the approach is leveraged by malicious actors for cybercrime\. We therefore propose and evaluate RedTeamLLM, an integrated architecture with a comprehensive security model for automatization of pentest tasks\. RedTeamLLM follows three key steps: summarizing, reasoning and act, which embed its operational capacity\. This novel framework addresses four open challenges: plan correction, memory management, context window constraint, and generality vs\. specialization\. Evaluation is performed through the automated resolution of a range of entry\-level, but not trivial, CTF challenges\. The contribution of the reasoning capability of our agentic AI framework is specifically evaluated\.

## Tasks

- [Penetration testing](https://paperswithcode-cyber.com/tasks/cyberintel-penetration-testing)

## Code repositories

- [lre\-security\-systems\-team/redteamllm](https://github.com/lre-security-systems-team/redteamllm)

## Paper resources

- [Abstract page](https://arxiv.org/abs/2505.06913v1)
- [PDF](https://arxiv.org/pdf/2505.06913v1.pdf)