STRIATUM-CTF: A Protocol-Driven Agentic Framework for General-Purpose CTF Solving
James Hugglestone, Samuel Jacob Chacko, Dawson Stoller, Ryan Schmidt, Xiuwen Liu

TL;DR
This paper introduces STRIATUM-CTF, a modular agentic framework utilizing a standardized protocol for real-time, multi-step cybersecurity problem solving, demonstrated by winning a Capture-the-Flag competition.
Contribution
The paper presents a novel, protocol-driven agentic framework that enhances LLM-based cybersecurity reasoning by standardizing tool interfaces and maintaining context across complex exploit trajectories.
Findings
Outperformed 21 human teams in a live CTF competition.
Reduced hallucination through MCP-based tool abstraction.
Demonstrated robustness in dynamic, real-world cybersecurity scenarios.
Abstract
Large Language Models (LLMs) have demonstrated potential in code generation, yet they struggle with the multi-step, stateful reasoning required for offensive cybersecurity operations. Existing research often relies on static benchmarks that fail to capture the dynamic nature of real-world vulnerabilities. In this work, we introduce STRIATUM-CTF (A Search-based Test-time Reasoning Inference Agent for Tactical Utility Maximization in Cybersecurity), a modular agentic framework built upon the Model Context Protocol (MCP). By standardizing tool interfaces for system introspection, decompilation, and runtime debugging, STRIATUM-CTF enables the agent to maintain a coherent context window across extended exploit trajectories. We validate this approach not merely on synthetic datasets, but in a live competitive environment. Our system participated in a university-hosted Capture-the-Flag (CTF)…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdversarial Robustness in Machine Learning · Information and Cyber Security · Security and Verification in Computing
