2 papers
cs.CR2026
MazeRunner: Nonlinear Task and Clue Orchestration for LLM-driven Black-Box Automated Penetration Testing
Zhenyuan Li, Yi Jiang, Junjie Cheng +3
Penetration testing is essential yet resource-intensive. Although large language models (LLMs) show promise for automating security auditing, existing agents mainly execute end-to-…
cs.CR2025
Automated Penetration Testing with LLM Agents and Classical Planning
Lingzhi Wang, Xinyi Shi, Ziyu Li +8
While penetration testing plays a vital role in cybersecurity, achieving fully automated, hands-off-the-keyboard execution remains a significant research challenge. In this paper,…