# Measuring and Augmenting Large Language Models for Solving Capture-the-Flag Challenges

arXiv: https://arxiv.org/abs/2506.17644 · HTML: https://mlsanity.com/paper/2506.17644/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 72 references that are in the map.
- First posted on arXiv 21 Jun 2025.

## Builds on (most cited first, 25 of 25)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Graph of Thoughts: Solving Elaborate Problems with Large Language Models](https://mlsanity.com/paper/2308.09687/) (2023)
- [The Power of Noise: Redefining Retrieval for RAG Systems](https://mlsanity.com/paper/2401.14887/) (2024)
- [Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security](https://mlsanity.com/paper/2401.05459/) (2024)
- [InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback](https://mlsanity.com/paper/2306.14898/) (2023)
- [Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models](https://mlsanity.com/paper/2311.09210/) (2023)
- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [Large Language Models are Zero-Shot Fuzzers: Fuzzing Deep-Learning Libraries via Large Language Models](https://mlsanity.com/paper/2212.14834/) (2022)
- [Teams of LLM Agents can Exploit Zero-Day Vulnerabilities](https://mlsanity.com/paper/2406.01637/) (2024)
- [Getting pwn'd by AI: Penetration Testing with Large Language Models](https://mlsanity.com/paper/2308.00121/) (2023)
- [GPTScan: Detecting Logic Vulnerabilities in Smart Contracts by Combining GPT with Program Analysis](https://mlsanity.com/paper/2308.03314/) (2023)
- [Understanding the Effectiveness of Large Language Models in Detecting Security Vulnerabilities](https://mlsanity.com/paper/2311.16169/) (2023)
- [LLM4Vuln: A Unified Evaluation Framework for Decoupling and Enhancing LLMs' Vulnerability Reasoning](https://mlsanity.com/paper/2401.16185/) (2024)
- [Combining Fine-Tuning and LLM-based Agents for Intuitive Smart Contract Auditing with Justifications](https://mlsanity.com/paper/2403.16073/) (2024)
- [Transformer-Based Language Models for Software Vulnerability Detection](https://mlsanity.com/paper/2204.03214/) (2022)
- [PropertyGPT: LLM-driven Formal Verification of Smart Contracts through Retrieval-Augmented Property Generation](https://mlsanity.com/paper/2405.02580/) (2024)
- [An Empirical Evaluation of LLMs for Solving Offensive Security Challenges](https://mlsanity.com/paper/2402.11814/) (2024)
- [PenHeal: A Two-Stage LLM Framework for Automated Pentesting and Optimal Remediation](https://mlsanity.com/paper/2407.17788/) (2024)
- [Using Large Language Models for Cybersecurity Capture-The-Flag Challenges and Certification Questions](https://mlsanity.com/paper/2308.10443/) (2023)
- [SecBench: A Comprehensive Multi-Dimensional Benchmarking Dataset for LLMs in Cybersecurity](https://mlsanity.com/paper/2412.20787/) (2024)
- [ACFIX: Guiding LLMs with Mined Common RBAC Practices for Context-Aware Repair of Access Control Vulnerabilities in Smart Contracts](https://mlsanity.com/paper/2403.06838/) (2024)
- [LLM for Mobile: An Initial Roadmap](https://mlsanity.com/paper/2407.06573/) (2024)
- [Benefits and Pitfalls of Using Capture the Flag Games in University Courses](https://mlsanity.com/paper/2004.11556/) (2020)
- [Thunder CTF: Learning Cloud Security on a Dime](https://mlsanity.com/paper/2107.12566/) (2021)

## Built on by (most cited first, 15 of 15)

- [SoK: Agentic Skills -- Beyond Tool Use in LLM Agents](https://mlsanity.com/paper/2602.20867/) (2026)
- [Silo-Bench: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systems](https://mlsanity.com/paper/2603.01045/) (2026)
- [CTFusion: A CTF-based Benchmark for LLM Agent Evaluation](https://mlsanity.com/paper/2605.11504/) (2026)
- [Capture the Flags: Family-Based Evaluation of Agentic LLMs via Semantics-Preserving Transformations](https://mlsanity.com/paper/2602.05523/) (2026)
- [CTFExplorer: Evaluating LLM Offensive Agents Through Multi-Target Web CTF Benchmarking](https://mlsanity.com/paper/2602.08023/) (2026)
- [KryptoPilot: An Open-World Knowledge-Augmented LLM Agent for Automated Cryptographic Exploitation](https://mlsanity.com/paper/2601.09129/) (2026)
- [Hallucination-Resistant Security Planning with a Large Language Model](https://mlsanity.com/paper/2602.05279/) (2026)
- [AI In Cybersecurity Education -- Scalable Agentic CTF Design Principles and Educational Outcomes](https://mlsanity.com/paper/2603.21551/) (2026)
- [Rethinking and Exploring String-Based Malware Family Classification in the Era of LLMs and RAG](https://mlsanity.com/paper/2507.04055/) (2025)
- [CyberEvolver: Structured Self-Evolution for Cybersecurity Agents On the Fly](https://mlsanity.com/paper/2605.26195/) (2026)
- [Poisoned Playbooks: Demystifying Knowledge Poisoning Effects on AI Security Agents](https://mlsanity.com/paper/2606.24402/) (2026)
- [The Disruptive Impact of Large Language Models on Capture the Flag Competitions and the Path Toward Fair Play](https://mlsanity.com/paper/2607.25425/) (2026)
- [PLCBench: Can Autonomous LLM Agents Turn PLC Access into Sustained Physical Impact?](https://mlsanity.com/paper/2608.26882/) (2026)
- [Reveree: Diagnosing LLM Reverse-Engineering Agents](https://mlsanity.com/paper/2609.01185/) (2026)
- [Humans vs. Machines: A Comparison With AI Agents in Software Reverse Engineering](https://mlsanity.com/paper/2610.14960/) (2026)

## Abstract (arXiv)

Capture-the-Flag (CTF) competitions are crucial for cybersecurity education and training. As large language models (LLMs) evolve, there is increasing interest in their ability to automate CTF challenge solving. For example, DARPA has organized the AIxCC competition since 2023 to advance AI-powered automated offense and defense. However, this demands a combination of multiple abilities, from knowledge to reasoning and further to actions. In this paper, we highlight the importance of technical knowledge in solving CTF problems and deliberately construct a focused benchmark, CTFKnow, with 3,992 questions to measure LLMs' performance in this core aspect. Our study offers a focused and innovative measurement of LLMs' capability in understanding CTF knowledge and applying it to solve CTF challenges. Our key findings reveal that while LLMs possess substantial technical knowledge, they falter in accurately applying this knowledge to specific scenarios and adapting their strategies based on feedback from the CTF environment. Based on insights derived from this measurement study, we propose CTFAgent, a novel LLM-driven framework for advancing CTF problem-solving. CTFAgent introduces two new modules: two-stage Retrieval Augmented Generation (RAG) and interactive Environmental Augmentation, which enhance LLMs' technical knowledge and vulnerability exploitation on CTF, respectively. Our experimental results show that, on two popular CTF datasets, CTFAgent both achieves over 80% performance improvement. Moreover, in the recent picoCTF2024 hosted by CMU, CTFAgent ranked in the top 23.6% of nearly 7,000 participating teams. This reflects the benefit of our measurement study and the potential of our framework in advancing LLMs' capabilities in CTF problem-solving.