mlsanityData to 7 Oct 2026

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

arXiv 2403.17674 ↗First posted 26 Mar 2024cs.CR cs.AI cs.MAcited by 20

On the map: LLM agents and tool use → Agent threats, guardrails and governance

Abstract (arXiv)

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. Additionally, it adopts the collaboration mechanism to take suggestions from pre-trained RL agents, including a cursor for dynamic suggestion taken, an aggregator for multiple mentors' suggestions ranking and a caller for proactive suggestion asking. Building on the CybORG experiment framework, our experiences show that SecurityBot demonstrates significant performance improvement compared with LLM or RL standalone, achieving the complementary performance in the cybersecurity games.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 30 of its 45 references that are in the map. First posted on arXiv 26 Mar 2024.

Builds on

30 of 45 references.

References · 30

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  3. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  4. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  5. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
  6. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  7. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  8. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  9. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  10. 2023Eureka: Human-Level Reward Design via Coding Large Language Modelscited by 542
  11. 2023A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Uglycited by 380
  12. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agentscited by 329
18 more
  1. 2023Reward Design with Language Modelscited by 257
  2. 2023Self-collaboration Code Generation via ChatGPTcited by 255
  3. 2023Exploring Large Language Models for Communication Games: An Empirical Study on Werewolfcited by 238
  4. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewcited by 221
  5. 2023Can LLM-Generated Misinformation Be Detected?cited by 173
  6. 2023JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Modelscited by 170
  7. 2023SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Taskscited by 166
  8. 2021Examining Zero-Shot Vulnerability Repair with Large Language Modelscited by 105
  9. 2023PentestGPT: An LLM-empowered Automatic Penetration Testing Toolcited by 94
  10. 2022Lost at C: A User Study on the Security Implications of Large Language Model Code Assistantscited by 87
  11. 2023Humanoid Agents: Platform for Simulating Human-like Generative Agentscited by 73
  12. 2023Collaborating with language models for embodied reasoningcited by 61
  13. 2021CybORG: A Gym for the Development of Autonomous Cyber Agentscited by 58
  14. 2023Enabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approachcited by 28
  15. 2023HuntGPT: Integrating Machine Learning-Based Anomaly Detection and Explainable AI with Large Language Models (LLMs)cited by 25
  16. 2022EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RLcited by 23
  17. 2023Decoding the Threat Landscape : ChatGPT, FraudGPT, and WormGPT in Social Engineering Attackscited by 22
  18. 2023Can Large Language Models Find And Fix Vulnerable Software?cited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 9; 2026: 7.

20 papers.

Sort:

By area:

  1. 2024Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systemscited by 129
  2. 2024G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networkscited by 110
  3. 2025Internet of Agents: Fundamentals, Applications, and Challengescited by 31
  4. 2025VulnBot: Autonomous Penetration Testing for A Multi-Agent Collaborative Frameworkcited by 30
  5. 2025AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Predictioncited by 25
  6. 2025MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machinescited by 17
  7. 2025Large Language Models are Autonomous Cyber Defenderscited by 14
  8. 2024Optimal Defender Strategies for CAGE-2 using Causal Modeling and Tree Searchcited by 12
  9. 2025Incident Response Planning Using a Lightweight Large Language Model with Reduced Hallucinationcited by 10
  10. 2026Live-Evo: Online Evolution of Agentic Memory from Continuous Feedbackcited by 8
  11. 2026EVA: Efficient Reinforcement Learning for End-to-End Video Agentcited by 5
  12. 2025A Short Survey on Small Reasoning Models: Training, Inference, Applications and Research Directionscited by 4
8 more
  1. 2026In-Context Autonomous Network Incident Response: An End-to-End Large Language Model Agent Approachcited by 4
  2. 2025ARCeR: an Agentic RAG for the Automated Definition of Cyber Rangescited by 3
  3. 2025Evaluating the Quality of Randomness and Entropy in Tasks Supported by Large Language Modelscited by 2
  4. 2024Countering Autonomous Cyber Threatscited by 1
  5. 2026Hallucination-Resistant Security Planning with a Large Language Modelcited by 1
  6. 2026Agentic Incident Response through Digital Twin-Enhanced Multiscale Planningcited by 1
  7. 2026COHORT: Collaborative Orchestration for Hardening via Offensive Replay on Emulated Topologiescited by 0
  8. 2026Rethinking Multi-Agent Collaboration: When More Is Lesscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Distilling Knowledge from Large Language Models into Lightweight Reinforcement Learning Agents for Autonomous Cyber Operations
  2. 2026LLM agents security duality: a comprehensive survey of self-security and empowered cybersecurity
  3. 2023Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments
  4. 2026Ask the Expert: LLM-Guided Reinforcement Learning for Autonomous Cyber Defense
  5. 2026Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)
  6. 2025How to Train Your LLM Web Agent: A Statistical Diagnosis
  7. 2025Cyber-Zero: Training Cybersecurity Agents without Runtime
  8. 2025Game Theory Meets LLM and Agentic AI: Reimagining Cybersecurity for the Age of Intelligent Threats