---
title: "AI Pentesting Tools & Cybersecurity Research — Page 4 | Papers With Code Cyber"
description: "Find AI pentesting tools, security agent harnesses, papers and benchmarks. Filter cybersecurity research by topic, target and contribution."
canonical: "https://paperswithcode-cyber.com/catalog?offset=75"
type: "catalog"
---

# Browse catalog

Find AI pentesting tools, security agent harnesses, papers and benchmarks\. Filter cybersecurity research by topic, target and contribution\. 189 papers\.

## Related research

- [Trending research](https://paperswithcode-cyber.com/)
- [Previous](https://paperswithcode-cyber.com/catalog?offset=50)
- [Next](https://paperswithcode-cyber.com/catalog?offset=100)

## Relevant papers

1. [Comparing AI Agents to Cybersecurity Professionals in Real\-World Penetration Testing](https://paperswithcode-cyber.com/paper/2512.09882) — 2025 · System or technique · Empirical study / experience
2. [PATCHEVAL: A New Benchmark for Evaluating LLMs on Patching Real\-World Vulnerabilities](https://paperswithcode-cyber.com/paper/2511.11019) — 2025 · Benchmark
3. [Cybersecurity AI Benchmark \(CAIBench\): A Meta\-Benchmark for Evaluating Cybersecurity AI Agents](https://paperswithcode-cyber.com/paper/2510.24317) — 2025 · Benchmark
4. [BlueCodeAgent: A Blue Teaming Agent Powered by Automated Red Teaming for CodeGen AI](https://paperswithcode-cyber.com/paper/2510.18131) — 2025 · System or technique
5. [HackWorld: Evaluating Computer\-Use Agents on Exploiting Web Application Vulnerabilities](https://paperswithcode-cyber.com/paper/2510.12200) — 2025 · Benchmark
6. [PACEbench: A Framework for Evaluating Practical AI Cyber\-Exploitation Capabilities](https://paperswithcode-cyber.com/paper/2510.11688) — 2025 · Benchmark
7. [AutoPentester: An LLM Agent\-based Framework for Automated Pentesting](https://paperswithcode-cyber.com/paper/2510.05605) — 2025 · System or technique
8. [PentestMCP: A Toolkit for Agentic Penetration Testing](https://paperswithcode-cyber.com/paper/2510.03610) — 2025 · System or technique
9. [ATLANTIS: AI\-driven Threat Localization, Analysis, and Triage Intelligence System](https://paperswithcode-cyber.com/paper/87) — 2025 · System or technique
10. [xOffense: An Autonomous Multi\-Agent Framework for Penetration Testing with Domain\-Adapted Large Language Models](https://paperswithcode-cyber.com/paper/60) — 2025 · System or technique
11. [Shell or Nothing: Real\-World Benchmarks and Memory\-Activated Agents for Automated Penetration Testing](https://paperswithcode-cyber.com/paper/91) — 2025 · System or technique · Benchmark · Empirical study / experience
12. [Guided Reasoning in LLM\-Driven Penetration Testing Using Structured Attack Trees](https://paperswithcode-cyber.com/paper/2509.07939) — 2025 · System or technique
13. [All You Need Is A Fuzzing Brain: An LLM\-Powered System for Automated Vulnerability Detection and Patching](https://paperswithcode-cyber.com/paper/2509.07225) — 2025 · System or technique · Benchmark
14. [From CVE Entries to Verifiable Exploits: An Automated Multi\-Agent Framework for Reproducing CVEs](https://paperswithcode-cyber.com/paper/2509.01835) — 2025 · System or technique · Dataset
15. [Multi\-Agent Penetration Testing AI for the Web](https://paperswithcode-cyber.com/paper/2508.20816) — 2025 · System or technique
16. [MultiFuzz: A Dense Retrieval\-based Multi\-Agent System for Network Protocol Fuzzing](https://paperswithcode-cyber.com/paper/65) — 2025 · System or technique
17. [Pentest\-R1: Towards Autonomous Penetration Testing Reasoning Optimized via Two\-Stage Reinforcement Learning](https://paperswithcode-cyber.com/paper/2508.07382) — 2025 · System or technique
18. [Towards Effective Offensive Security LLM Agents: Hyperparameter Tuning, LLM as a Judge, and a Lightweight CTF Benchmark](https://paperswithcode-cyber.com/paper/2508.05674) — 2025 · Empirical study / experience · Benchmark
19. [ASTRA: Autonomous Spatial\-Temporal Red\-teaming for AI Software Assistants](https://paperswithcode-cyber.com/paper/2508.03936) — 2025 · System or technique
20. [Cyber\-Zero: Training Cybersecurity Agents without Runtime](https://paperswithcode-cyber.com/paper/2508.00910) — 2025 · System or technique