# Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments

arXiv: https://arxiv.org/abs/2308.12086 · HTML: https://mlsanity.com/paper/2308.12086/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 53 references that are in the map.
- First posted on arXiv 23 Aug 2023.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents](https://mlsanity.com/paper/2302.01560/) (2023)
- [How is ChatGPT's behavior changing over time?](https://mlsanity.com/paper/2307.09009/) (2023)
- [Benchmarking the Spectrum of Agent Capabilities](https://mlsanity.com/paper/2109.06780/) (2021)
- [Guiding Pretraining in Reinforcement Learning with Large Language Models](https://mlsanity.com/paper/2302.06692/) (2023)
- [Examining Zero-Shot Vulnerability Repair with Large Language Models](https://mlsanity.com/paper/2112.02125/) (2021)
- [Getting pwn'd by AI: Penetration Testing with Large Language Models](https://mlsanity.com/paper/2308.00121/) (2023)
- [CybORG: A Gym for the Development of Autonomous Cyber Agents](https://mlsanity.com/paper/2108.09118/) (2021)
- [Housekeep: Tidying Virtual Households using Commonsense Reasoning](https://mlsanity.com/paper/2205.10712/) (2022)
- [Transformer-Based Language Models for Software Vulnerability Detection](https://mlsanity.com/paper/2204.03214/) (2022)
- [Developing Optimal Causal Cyber-Defence Agents via Cyber Security Simulation](https://mlsanity.com/paper/2207.12355/) (2022)
- [Autonomous Penetration Testing using Reinforcement Learning](https://mlsanity.com/paper/1905.05965/) (2019)
- [Finding Effective Security Strategies through Reinforcement Learning and Self-Play](https://mlsanity.com/paper/2009.08120/) (2020)
- [NASimEmu: Network Attack Simulator & Emulator for Training Agents Generalizing to Novel Scenarios](https://mlsanity.com/paper/2305.17246/) (2023)

## Built on by (most cited first, 18 of 18)

- [When LLMs Meet Cybersecurity: A Systematic Literature Review](https://mlsanity.com/paper/2405.03644/) (2024)
- [Large Language Models are Autonomous Cyber Defenders](https://mlsanity.com/paper/2505.04843/) (2025)
- [ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation](https://mlsanity.com/paper/2507.14201/) (2025)
- [Optimal Defender Strategies for CAGE-2 using Causal Modeling and Tree Search](https://mlsanity.com/paper/2407.11070/) (2024)
- [Incident Response Planning Using a Lightweight Large Language Model with Reduced Hallucination](https://mlsanity.com/paper/2508.05188/) (2025)
- [Hackphyr: A Local Fine-Tuned LLM Agent for Network Security Environments](https://mlsanity.com/paper/2409.11276/) (2024)
- [Scalable Learning of Intrusion Responses through Recursive Decomposition](https://mlsanity.com/paper/2309.03292/) (2023)
- [A Survey of Large Language Models in Cybersecurity](https://mlsanity.com/paper/2402.16968/) (2024)
- [Intrusion Tolerance for Networked Systems through Two-Level Feedback Control](https://mlsanity.com/paper/2404.01741/) (2024)
- [Online Incident Response Planning under Model Misspecification through Bayesian Learning and Belief Quantization](https://mlsanity.com/paper/2508.14385/) (2025)
- [AttacKG+:Boosting Attack Knowledge Graph Construction with Large Language Models](https://mlsanity.com/paper/2405.04753/) (2024)
- [Boardwalk Empire: How Generative AI is Revolutionizing Economic Paradigms](https://mlsanity.com/paper/2410.15212/) (2024)
- [Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents](https://mlsanity.com/paper/2604.27143/) (2026)
- [A Red Teaming Framework for Evaluating Robustness of AI-enabled Security Orchestration, Automation, and Response Systems](https://mlsanity.com/paper/2605.17075/) (2026)
- [From Capabilities to Performance: Evaluating Key Functional Properties of LLM Architectures in Penetration Testing](https://mlsanity.com/paper/2509.14289/) (2025)
- [Evaluating Generalization Mechanisms in Autonomous Cyber Attack Agents](https://mlsanity.com/paper/2603.10041/) (2026)
- [COHORT: Collaborative Orchestration for Hardening via Offensive Replay on Emulated Topologies](https://mlsanity.com/paper/2606.30479/) (2026)
- [No One Architecture Fits All: A Cross-Environment Evaluation of Hierarchical Red Team Agents](https://mlsanity.com/paper/2610.00557/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have gained widespread popularity across diverse domains involving text generation, summarization, and various natural language processing tasks. Despite their inherent limitations, LLM-based designs have shown promising capabilities in planning and navigating open-world scenarios. This paper introduces a novel application of pre-trained LLMs as agents within cybersecurity network environments, focusing on their utility for sequential decision-making processes. We present an approach wherein pre-trained LLMs are leveraged as attacking agents in two reinforcement learning environments. Our proposed agents demonstrate similar or better performance against state-of-the-art agents trained for thousands of episodes in most scenarios and configurations. In addition, the best LLM agents perform similarly to human testers of the environment without any additional training process. This design highlights the potential of LLMs to efficiently address complex decision-making tasks within cybersecurity. Furthermore, we introduce a new network security environment named NetSecGame. The environment is designed to eventually support complex multi-agent scenarios within the network security domain. The proposed environment mimics real network attacks and is designed to be highly modular and adaptable for various scenarios.