# PACEbench: A Framework for Evaluating Practical AI Cyber-Exploitation Capabilities

arXiv: https://arxiv.org/abs/2510.11688 · HTML: https://mlsanity.com/paper/2510.11688/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 24 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Builds on (most cited first, 16 of 16)

- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attacks](https://mlsanity.com/paper/2403.01038/) (2024)
- [CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities](https://mlsanity.com/paper/2503.17332/) (2025)
- [NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security](https://mlsanity.com/paper/2406.05590/) (2024)
- [RedCode: Risky Code Execution and Generation Benchmark for Code Agents](https://mlsanity.com/paper/2411.07781/) (2024)
- [CyberMetric: A Benchmark Dataset based on Retrieval-Augmented Generation for Evaluating LLMs in Cybersecurity Knowledge](https://mlsanity.com/paper/2402.07688/) (2024)
- [EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities](https://mlsanity.com/paper/2409.16165/) (2024)
- [PentestAgent: Incorporating LLM Agents to Automated Penetration Testing](https://mlsanity.com/paper/2411.05185/) (2024)
- [BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems](https://mlsanity.com/paper/2505.15216/) (2025)
- [HackSynth: LLM Agent and Evaluation Framework for Autonomous Penetration Testing](https://mlsanity.com/paper/2412.01778/) (2024)
- [VulnBot: Autonomous Penetration Testing for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2501.13411/) (2025)
- [AutoPenBench: Benchmarking Generative Agents for Penetration Testing](https://mlsanity.com/paper/2410.03225/) (2024)
- [SecBench: A Comprehensive Multi-Dimensional Benchmarking Dataset for LLMs in Cybersecurity](https://mlsanity.com/paper/2412.20787/) (2024)
- [Forewarned is Forearmed: A Survey on Large Language Model-based Agents in Autonomous Cyberattacks](https://mlsanity.com/paper/2505.12786/) (2025)
- [RapidPen: Fully Automated IP-to-Shell Penetration Testing with LLM-based Agents](https://mlsanity.com/paper/2502.16730/) (2025)

## Built on by (most cited first, 7 of 7)

- [Quantifying Frontier LLM Capabilities for Container Sandbox Escape](https://mlsanity.com/paper/2603.02277/) (2026)
- [Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testing](https://mlsanity.com/paper/2604.05719/) (2026)
- [SIR-Bench: Evaluating Investigation Depth in Security Incident Response Agents](https://mlsanity.com/paper/2604.12040/) (2026)
- [A New Framework for Cybersecurity Refusals in AI Agents](https://mlsanity.com/paper/2606.02644/) (2026)
- [RangeFactory: Scalable Construction of Multi-Hop Cyber Ranges](https://mlsanity.com/paper/2608.09526/) (2026)
- [Terminal Agents: A Survey of AI Agents in Command-Line Environments](https://mlsanity.com/paper/2608.20485/) (2026)
- [From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World](https://mlsanity.com/paper/2605.10834/) (2026)

## Abstract (arXiv)

The increasing autonomy of Large Language Models (LLMs) necessitates a rigorous evaluation of their potential to aid in cyber offense. Existing benchmarks often lack real-world complexity and are thus unable to accurately assess LLMs' cybersecurity capabilities. To address this gap, we introduce PACEbench, a practical AI cyber-exploitation benchmark built on the principles of realistic vulnerability difficulty, environmental complexity, and cyber defenses. Specifically, PACEbench comprises four scenarios spanning single, blended, chained, and defense vulnerability exploitations. To handle these complex challenges, we propose PACEagent, a novel agent that emulates human penetration testers by supporting multi-phase reconnaissance, analysis, and exploitation. Extensive experiments with seven frontier LLMs demonstrate that current models struggle with complex cyber scenarios, and none can bypass defenses. These findings suggest that current models do not yet pose a generalized cyber offense threat. Nonetheless, our work provides a robust benchmark to guide the trustworthy development of future models.