English

What Makes a Good LLM Agent for Real-world Penetration Testing?

Cryptography and Security 2026-02-20 v1 Software Engineering

Abstract

LLM-based agents show promise for automating penetration testing, yet reported performance varies widely across systems and benchmarks. We analyze 28 LLM-based penetration testing systems and evaluate five representative implementations across three benchmarks of increasing complexity. Our analysis reveals two distinct failure modes: Type A failures stem from capability gaps (missing tools, inadequate prompts) that engineering readily addresses, while Type B failures persist regardless of tooling due to planning and state management limitations. We show that Type B failures share a root cause that is largely invariant to the underlying LLM: agents lack real-time task difficulty estimation. As a result, agents misallocate effort, over-commit to low-value branches, and exhaust context before completing attack chains. Based on this insight, we present Excalibur, a penetration testing agent that couples strong tooling with difficulty-aware planning. A Tool and Skill Layer eliminates Type A failures through typed interfaces and retrieval-augmented knowledge. A Task Difficulty Assessment (TDA) mechanism addresses Type B failures by estimating tractability through four measurable dimensions (horizon estimation, evidence confidence, context load, and historical success) and uses these estimates to guide exploration-exploitation decisions within an Evidence-Guided Attack Tree Search (EGATS) framework. Excalibur achieves up to 91% task completion on CTF benchmarks with frontier models (39 to 49% relative improvement over baselines) and compromises 4 of 5 hosts on the GOAD Active Directory environment versus 2 by prior systems. These results show that difficulty-aware planning yields consistent end-to-end gains across models and addresses a limitation that model scaling alone does not eliminate.

Keywords

Cite

@article{arxiv.2602.17622,
  title  = {What Makes a Good LLM Agent for Real-world Penetration Testing?},
  author = {Gelei Deng and Yi Liu and Yuekang Li and Ruozhao Yang and Xiaofei Xie and Jie Zhang and Han Qiu and Tianwei Zhang},
  journal= {arXiv preprint arXiv:2602.17622},
  year   = {2026}
}
R2 v1 2026-07-01T10:43:19.221Z