mlsanityData to 14 Oct 2026

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

arXiv 2506.17644 ↗First posted 21 Jun 2025cs.AIcited by 15

Not on the map. Why?

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.

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

25 of 72 references.

References · 25

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  3. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 886
  4. 2024The Power of Noise: Redefining Retrieval for RAG Systemscited by 281
  5. 2024Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Securitycited by 260
  6. 2023InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedbackcited by 238
  7. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 184
  8. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 126
  9. 2022Large Language Models are Zero-Shot Fuzzers: Fuzzing Deep-Learning Libraries via Large Language Modelscited by 103
  10. 2024Teams of LLM Agents can Exploit Zero-Day Vulnerabilitiescited by 95
  11. 2023Getting pwn'd by AI: Penetration Testing with Large Language Modelscited by 83
  12. 2023GPTScan: Detecting Logic Vulnerabilities in Smart Contracts by Combining GPT with Program Analysiscited by 65
13 more
  1. 2023Understanding the Effectiveness of Large Language Models in Detecting Security Vulnerabilitiescited by 59
  2. 2024LLM4Vuln: A Unified Evaluation Framework for Decoupling and Enhancing LLMs' Vulnerability Reasoningcited by 59
  3. 2024Combining Fine-Tuning and LLM-based Agents for Intuitive Smart Contract Auditing with Justificationscited by 41
  4. 2022Transformer-Based Language Models for Software Vulnerability Detectioncited by 39
  5. 2024PropertyGPT: LLM-driven Formal Verification of Smart Contracts through Retrieval-Augmented Property Generationcited by 37
  6. 2024An Empirical Evaluation of LLMs for Solving Offensive Security Challengescited by 35
  7. 2024PenHeal: A Two-Stage LLM Framework for Automated Pentesting and Optimal Remediationcited by 30
  8. 2023Using Large Language Models for Cybersecurity Capture-The-Flag Challenges and Certification Questionscited by 23
  9. 2024SecBench: A Comprehensive Multi-Dimensional Benchmarking Dataset for LLMs in Cybersecuritycited by 21
  10. 2024ACFIX: Guiding LLMs with Mined Common RBAC Practices for Context-Aware Repair of Access Control Vulnerabilities in Smart Contractscited by 15
  11. 2024LLM for Mobile: An Initial Roadmapcited by 11
  12. 2020Benefits and Pitfalls of Using Capture the Flag Games in University Coursescited by 6
  13. 2021Thunder CTF: Learning Cloud Security on a Dimecited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 14.

15 papers.

Sort:

By area:

  1. 2026SoK: Agentic Skills -- Beyond Tool Use in LLM Agentscited by 130
  2. 2026Silo-Bench: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systemscited by 20
  3. 2026CTFusion: A CTF-based Benchmark for LLM Agent Evaluationcited by 4
  4. 2026Capture the Flags: Family-Based Evaluation of Agentic LLMs via Semantics-Preserving Transformationscited by 3
  5. 2026CTFExplorer: Evaluating LLM Offensive Agents Through Multi-Target Web CTF Benchmarkingcited by 3
  6. 2026KryptoPilot: An Open-World Knowledge-Augmented LLM Agent for Automated Cryptographic Exploitationcited by 1
  7. 2026Hallucination-Resistant Security Planning with a Large Language Modelcited by 1
  8. 2026AI In Cybersecurity Education -- Scalable Agentic CTF Design Principles and Educational Outcomescited by 1
  9. 2025Rethinking and Exploring String-Based Malware Family Classification in the Era of LLMs and RAGcited by 0
  10. 2026CyberEvolver: Structured Self-Evolution for Cybersecurity Agents On the Flycited by 0
  11. 2026Poisoned Playbooks: Demystifying Knowledge Poisoning Effects on AI Security Agentscited by 0
  12. 2026The Disruptive Impact of Large Language Models on Capture the Flag Competitions and the Path Toward Fair Playcited by 0
3 more
  1. 2026PLCBench: Can Autonomous LLM Agents Turn PLC Access into Sustained Physical Impact?cited by 0
  2. 2026Reveree: Diagnosing LLM Reverse-Engineering Agentscited by 0
  3. 2026Humans vs. Machines: A Comparison With AI Agents in Software Reverse Engineeringcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security
  2. 2026Can AI Lower the Barrier to Cybersecurity? A Human-Centered Mixed-Methods Study of Novice CTF Learning
  3. 2025Towards Effective Offensive Security LLM Agents: Hyperparameter Tuning, LLM as a Judge, and a Lightweight CTF Benchmark
  4. 2025CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution
  5. 2025D-CIPHER: Dynamic Collaborative Intelligent Multi-Agent System with Planner and Heterogeneous Executors for Offensive Security
  6. 2026Do Agents Dream of Root Shells? Partial-Credit Evaluation of LLM Agents in Capture the Flag Challenges
  7. 2026STRIATUM-CTF: A Protocol-Driven Agentic Framework for General-Purpose CTF Solving
  8. 2026Autonomous LLM Agents & CTFs: A Second Look