Saved in:
Bibliographic Details
Main Authors: Luong, Phung Duc, Bao, Le Tran Gia, Tam, Nguyen Vu Khai, Khoa, Dong Huu Nguyen, Quyen, Nguyen Huu, Pham, Van-Hau, Duy, Phan The
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.13021
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917438011998208
author Luong, Phung Duc
Bao, Le Tran Gia
Tam, Nguyen Vu Khai
Khoa, Dong Huu Nguyen
Quyen, Nguyen Huu
Pham, Van-Hau
Duy, Phan The
author_facet Luong, Phung Duc
Bao, Le Tran Gia
Tam, Nguyen Vu Khai
Khoa, Dong Huu Nguyen
Quyen, Nguyen Huu
Pham, Van-Hau
Duy, Phan The
contents This work introduces xOffense, an AI-driven, multi-agent penetration testing framework that shifts the process from labor-intensive, expert-driven manual efforts to fully automated, machine-executable workflows capable of scaling seamlessly with computational infrastructure. At its core, xOffense leverages a fine-tuned, mid-scale open-source LLM (Qwen3-32B) to drive reasoning and decision-making in penetration testing. The framework assigns specialized agents to reconnaissance, vulnerability scanning, and exploitation, with an orchestration layer ensuring seamless coordination across phases. Fine-tuning on Chain-of-Thought penetration testing data further enables the model to generate precise tool commands and perform consistent multi-step reasoning. We evaluate xOffense on two rigorous benchmarks: AutoPenBench and AI-Pentest-Benchmark. The results demonstrate that xOffense consistently outperforms contemporary methods, achieving a sub-task completion rate of 79.17%, decisively surpassing leading systems such as VulnBot and PentestGPT. These findings highlight the potential of domain-adapted mid-scale LLMs, when embedded within structured multi-agent orchestration, to deliver superior, cost-efficient, and reproducible solutions for autonomous penetration testing.
format Preprint
id arxiv_https___arxiv_org_abs_2509_13021
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle xOffense: An Autonomous Multi-Agent Framework for Penetration Testing with Domain-Adapted Large Language Models
Luong, Phung Duc
Bao, Le Tran Gia
Tam, Nguyen Vu Khai
Khoa, Dong Huu Nguyen
Quyen, Nguyen Huu
Pham, Van-Hau
Duy, Phan The
Cryptography and Security
Artificial Intelligence
This work introduces xOffense, an AI-driven, multi-agent penetration testing framework that shifts the process from labor-intensive, expert-driven manual efforts to fully automated, machine-executable workflows capable of scaling seamlessly with computational infrastructure. At its core, xOffense leverages a fine-tuned, mid-scale open-source LLM (Qwen3-32B) to drive reasoning and decision-making in penetration testing. The framework assigns specialized agents to reconnaissance, vulnerability scanning, and exploitation, with an orchestration layer ensuring seamless coordination across phases. Fine-tuning on Chain-of-Thought penetration testing data further enables the model to generate precise tool commands and perform consistent multi-step reasoning. We evaluate xOffense on two rigorous benchmarks: AutoPenBench and AI-Pentest-Benchmark. The results demonstrate that xOffense consistently outperforms contemporary methods, achieving a sub-task completion rate of 79.17%, decisively surpassing leading systems such as VulnBot and PentestGPT. These findings highlight the potential of domain-adapted mid-scale LLMs, when embedded within structured multi-agent orchestration, to deliver superior, cost-efficient, and reproducible solutions for autonomous penetration testing.
title xOffense: An Autonomous Multi-Agent Framework for Penetration Testing with Domain-Adapted Large Language Models
topic Cryptography and Security
Artificial Intelligence
url https://arxiv.org/abs/2509.13021