@article{benchmarkingpracticesinllmdriven, title = {Benchmarking Practices in LLM-driven Offensive Security: Testbeds, Metrics, and Experiment Design}, author = {Andreas Happe and Jürgen Cito}, year = {2025}, eprint = {2504.10112}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.10112v2}, }