---
title: "AI Pentesting Tools & Cybersecurity Research — Page 5 | 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=100"
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=75)
- [Next](https://paperswithcode-cyber.com/catalog?offset=125)

## Relevant papers

1. [CyberGym: Evaluating AI Agents' Real\-World Cybersecurity Capabilities at Scale](https://paperswithcode-cyber.com/paper/2506.02548) — 2025 · Benchmark · Dataset
2. [Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges](https://paperswithcode-cyber.com/paper/2506.02048) — 2025 · Dataset · System or technique
3. [Evaluating AI cyber capabilities with crowdsourced elicitation](https://paperswithcode-cyber.com/paper/2505.19915) — 2025 · Empirical study / experience
4. [Dynamic Risk Assessments for Offensive Cybersecurity Agents](https://paperswithcode-cyber.com/paper/2505.18384) — 2025 · Empirical study / experience
5. [BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real\-World Cybersecurity Systems](https://paperswithcode-cyber.com/paper/2505.15216) — 2025 · Benchmark
6. [CRAKEN: Cybersecurity LLM Agent with Knowledge\-Based Execution](https://paperswithcode-cyber.com/paper/2505.17107) — 2025 · System or technique
7. [ACSE\-Eval: Can LLMs threat model real\-world cloud infrastructure?](https://paperswithcode-cyber.com/paper/2505.11565) — 2025 · Benchmark
8. [AutoPentest: Enhancing Vulnerability Management With Autonomous LLM Agents](https://paperswithcode-cyber.com/paper/2505.10321) — 2025 · System or technique
9. [RedTeamLLM: an Agentic AI framework for offensive security](https://paperswithcode-cyber.com/paper/2505.06913) — 2025 · System or technique
10. [CAI: An Open, Bug Bounty\-Ready Cybersecurity AI](https://paperswithcode-cyber.com/paper/2504.06017) — 2025 · System or technique
11. [CVE\-Bench: A Benchmark for AI Agents' Ability to Exploit Real\-World Web Application Vulnerabilities](https://paperswithcode-cyber.com/paper/68) — 2025 · System or technique · Benchmark
12. [D\-CIPHER: Dynamic Collaborative Intelligent Multi\-Agent System with Planner and Heterogeneous Executors for Offensive Security](https://paperswithcode-cyber.com/paper/2502.10931) — 2025 · System or technique
13. [Can LLMs Hack Enterprise Networks? Autonomous Assumed Breach Penetration\-Testing Active Directory Networks](https://paperswithcode-cyber.com/paper/69) — 2025 · System or technique · Empirical study / experience
14. [Incalmo: An Autonomous LLM\-assisted System for Red Teaming Multi\-Host Networks](https://paperswithcode-cyber.com/paper/2501.16466) — 2025 · System or technique · Benchmark
15. [VulnBot: Autonomous Penetration Testing for A Multi\-Agent Collaborative Framework](https://paperswithcode-cyber.com/paper/59) — 2025 · System or technique
16. [AutoPenBench: A Vulnerability Testing Benchmark for Generative Agents](https://paperswithcode-cyber.com/paper/67) — 2025 · System or technique · Benchmark
17. [Mind the Gap: Towards Generalizable Autonomous Penetration Testing via Domain Randomization and Meta\-Reinforcement Learning](https://paperswithcode-cyber.com/paper/2412.04078) — 2024 · System or technique
18. [Hacking CTFs with Plain Agents](https://paperswithcode-cyber.com/paper/2412.02776) — 2024 · Empirical study / experience
19. [HackSynth: LLM Agent and Evaluation Framework for Autonomous Penetration Testing](https://paperswithcode-cyber.com/paper/2412.01778) — 2024 · System or technique · Benchmark
20. [CKGFuzzer: LLM\-Based Fuzz Driver Generation Enhanced By Code Knowledge Graph](https://paperswithcode-cyber.com/paper/2411.11532) — 2024 · System or technique