---
title: "STRIATUM-CTF: A Protocol-Driven Agentic Framework for General-Purpose CTF Solving (arXiv:2603.22577) | Papers With Code Cyber"
description: "Large Language Models (LLMs) have demonstrated potential in code generation, yet they struggle with the multi-step, stateful reasoning required for offensive cybersecurity…"
canonical: "https://paperswithcode-cyber.com/paper/2603.22577"
type: "paper"
---

# STRIATUM\-CTF: A Protocol\-Driven Agentic Framework for General\-Purpose CTF Solving

arXiv:2603\.22577 · 2026-03-23

Authors: James Hugglestone, Samuel Jacob Chacko, Dawson Stoller, Ryan Schmidt, Xiuwen Liu

## 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 \(CTF\) competition in late 2025, where it operated autonomously to identify and exploit vulnerabilities in real\-time\. STRIATUM\-CTF secured First Place, outperforming 21 human teams and demonstrating strong adaptability in a dynamic problem\-solving setting\. We analyze the agent's decision\-making logs to show how MCP\-based tool abstraction significantly reduces hallucination compared to naive prompting strategies\. These results suggest that standardized context protocols are a critical path toward robust autonomous cyber\-reasoning systems\.

## Tasks

- [Binary analysis](https://paperswithcode-cyber.com/tasks/cyberintel-binary-analysis)
- [Penetration testing](https://paperswithcode-cyber.com/tasks/cyberintel-penetration-testing)

## Code repositories

- [jawh3/striatum\-ctf](https://github.com/jawh3/striatum-ctf)

## Paper resources

- [Abstract page](https://arxiv.org/abs/2603.22577v1)
- [PDF](https://arxiv.org/pdf/2603.22577v1.pdf)