# Cyber-Zero: Training Cybersecurity Agents without Runtime

arXiv: https://arxiv.org/abs/2508.00910 · HTML: https://mlsanity.com/paper/2508.00910/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 28 of its 53 references that are in the map.
- First posted on arXiv 29 Jul 2025.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

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

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [StarCoder 2 and The Stack v2: The Next Generation](https://mlsanity.com/paper/2402.19173/) (2024)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [Training Software Engineering Agents and Verifiers with SWE-Gym](https://mlsanity.com/paper/2412.21139/) (2024)
- [SWE-smith: Scaling Data for Software Engineering Agents](https://mlsanity.com/paper/2504.21798/) (2025)
- [SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution](https://mlsanity.com/paper/2502.18449/) (2025)
- [NeMo: a toolkit for building AI applications using Neural Modules](https://mlsanity.com/paper/1909.09577/) (2019)
- [Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models](https://mlsanity.com/paper/2312.04724/) (2023)
- [Evaluating Frontier Models for Dangerous Capabilities](https://mlsanity.com/paper/2403.13793/) (2024)
- [An Adversarial Perspective on Machine Unlearning for AI Safety](https://mlsanity.com/paper/2409.18025/) (2024)
- [LLM Agents can Autonomously Hack Websites](https://mlsanity.com/paper/2402.06664/) (2024)
- [SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution](https://mlsanity.com/paper/2501.05040/) (2025)
- [Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement](https://mlsanity.com/paper/2411.00622/) (2024)
- [CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models](https://mlsanity.com/paper/2408.01605/) (2024)
- [On Evaluating the Durability of Safeguards for Open-Weight LLMs](https://mlsanity.com/paper/2412.07097/) (2024)
- [SecQA: A Concise Question-Answering Dataset for Evaluating Large Language Models in Computer Security](https://mlsanity.com/paper/2312.15838/) (2023)
- [From Text to MITRE Techniques: Exploring the Malicious Use of Large Language Models for Generating Cyber Attack Payloads](https://mlsanity.com/paper/2305.15336/) (2023)
- [Astraios: Parameter-Efficient Instruction Tuning Code Large Language Models](https://mlsanity.com/paper/2401.00788/) (2024)
- [AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses](https://mlsanity.com/paper/2503.01811/) (2025)
- [CAI: An Open, Bug Bounty-Ready Cybersecurity AI](https://mlsanity.com/paper/2504.06017/) (2025)
- [SecRepoBench: Benchmarking Code Agents for Secure Code Completion in Real-World Repositories](https://mlsanity.com/paper/2504.21205/) (2025)
- [SeCodePLT: A Unified Platform for Evaluating the Security of Code GenAI](https://mlsanity.com/paper/2410.11096/) (2024)

## Built on by (most cited first, 22 of 22)

- [Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?](https://mlsanity.com/paper/2607.09996/) (2026)
- [Training Language Model Agents to Find Vulnerabilities with CTF-Dojo](https://mlsanity.com/paper/2508.18370/) (2025)
- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [Uncovering Vulnerabilities of LLM-Assisted Cyber Threat Intelligence](https://mlsanity.com/paper/2509.23573/) (2025)
- [Watermarking LLM Agent Trajectories](https://mlsanity.com/paper/2602.18700/) (2026)
- [HackWorld: Evaluating Computer-Use Agents on Exploiting Web Application Vulnerabilities](https://mlsanity.com/paper/2510.12200/) (2025)
- [AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Penetration Agents](https://mlsanity.com/paper/2607.26998/) (2026)
- [PenForge: On-the-Fly Expert Agent Construction for Automated Penetration Testing](https://mlsanity.com/paper/2601.06910/) (2026)
- [To Defend Against Cyber Attacks, We Must Teach AI Agents to Hack](https://mlsanity.com/paper/2602.02595/) (2026)
- [Towards a Neural Debugger for Python](https://mlsanity.com/paper/2603.09951/) (2026)
- [AI In Cybersecurity Education -- Scalable Agentic CTF Design Principles and Educational Outcomes](https://mlsanity.com/paper/2603.21551/) (2026)
- [Challenges and Future Directions in Agentic Reverse Engineering Systems](https://mlsanity.com/paper/2604.14317/) (2026)
- [Themis: Training Robust Multilingual Code Reward Models for Flexible Multi-Criteria Scoring](https://mlsanity.com/paper/2605.00754/) (2026)
- [Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)](https://mlsanity.com/paper/2608.04317/) (2026)
- [RangeFactory: Scalable Construction of Multi-Hop Cyber Ranges](https://mlsanity.com/paper/2608.09526/) (2026)
- [Coherence-driven inference for cybersecurity](https://mlsanity.com/paper/2509.18520/) (2025)
- [XekRung Technical Report](https://mlsanity.com/paper/2605.00072/) (2026)
- [CyberEvolver: Structured Self-Evolution for Cybersecurity Agents On the Fly](https://mlsanity.com/paper/2605.26195/) (2026)
- [Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction](https://mlsanity.com/paper/2607.01764/) (2026)
- [CyberForge: Verified Vulnerability Injection at Repository Level for Cybersecurity Agent Training](https://mlsanity.com/paper/2608.06471/) (2026)
- [CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild](https://mlsanity.com/paper/2608.23181/) (2026)
- [Staying on the Attack Path: Structured State for Long-Horizon Automated Penetration Testing](https://mlsanity.com/paper/2609.07344/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have achieved remarkable success in software engineering tasks when trained with executable runtime environments, particularly in resolving GitHub issues. However, such runtime environments are often unavailable in other domains, especially cybersecurity, where challenge configurations and execution contexts are ephemeral or restricted. We present Cyber-Zero, the first runtime-free framework for synthesizing high-quality agent trajectories to train cybersecurity LLMs. Cyber-Zero leverages publicly available CTF writeups and employs persona-driven LLM simulation to reverse-engineer runtime behaviors and generate realistic, long-horizon interaction sequences without actual environments. Using trajectories synthesized by Cyber-Zero, we train LLM-based agents that achieve up to 13.1% absolute performance gains over baseline models on three prominent CTF benchmarks: InterCode-CTF, NYU CTF Bench, and Cybench. Our best model, Cyber-Zero-32B, establishes new state-of-the-art performance among open-weight models, matching the capabilities of proprietary systems like DeepSeek-V3-0324 and Claude-3.5-Sonnet while offering superior cost-effectiveness, and demonstrating that runtime-free trajectory synthesis can effectively democratize the development of state-of-the-art cybersecurity agents.