Depending on yourself when you should: Mentoring LLM with RL agents to become the master in cybersecurity games

arXiv:2403.17674v1 Announce Type: new
Abstract: Integrating LLM and reinforcement learning (RL) agent effectively to achieve complementary performance is critical in high stake tasks like cybersecurity operations. In this study, we introduce SecurityBot, a LLM agent mentored by pre-trained RL agents, to support cybersecurity operations. In particularly, the LLM agent is supported with a profile module to generated behavior guidelines, a memory module to accumulate local experiences, a reflection module to re-evaluate choices, and an action module to reduce action space. …

agent agents arxiv critical cs.ai cs.cr cs.ma cybersecurity effectively games high llm master mentoring operations performance stake study support