cs.CRJul 29, 2025

Cyber-Zero: Training Cybersecurity Agents without Runtime

Authors: Terry Yue Zhuo, Dingmin Wang, Hantian Ding, Varun Kumar, Zijian Wang

Organizations: Monash University · AWS AI Labs

Abstract

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 11.4% 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.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild

    Aug 24, 2026Jian Yang, Haau-Sing Li, Shawn Guo +10Automated Exploit GenerationCybersecurity

  2. ZeroDayBench: Evaluating LLM Agents on Unseen Zero-Day Vulnerabilities for Cyberdefense

    Mar 2, 2026Nancy Lau, Louis Sloot, Jyoutir Raj +6AI Agent Security BenchmarksLLMs for Cybersecurity

  3. STRIATUM-CTF: A Protocol-Driven Agentic Framework for Autonomous CTF Solving

    Mar 23, 2026James Hugglestone, Samuel Jacob Chacko, Dawson Stoller +2LLMs for CybersecurityLLM Agents