# Patch-to-PoC: A Systematic Study of Agentic LLM Systems for Linux Kernel N-Day Reproduction

arXiv: https://arxiv.org/abs/2602.07287 · HTML: https://mlsanity.com/paper/2602.07287/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 63 references that are in the map.
- First posted on arXiv 7 Feb 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 14 of 14)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024)
- [From CVE Entries to Verifiable Exploits: An Automated Multi-Agent Framework for Reproducing CVEs](https://mlsanity.com/paper/2509.01835/) (2025)
- [PoCGen: Generating Proof-of-Concept Exploits for Vulnerabilities in Npm Packages](https://mlsanity.com/paper/2506.04962/) (2025)
- [FaultLine: Automated Proof-of-Vulnerability Generation Using LLM Agents](https://mlsanity.com/paper/2507.15241/) (2025)
- [ATLANTIS: AI-driven Threat Localization, Analysis, and Triage Intelligence System](https://mlsanity.com/paper/2509.14589/) (2025)
- [All You Need Is A Fuzzing Brain: An LLM-Powered System for Automated Vulnerability Detection and Patching](https://mlsanity.com/paper/2509.07225/) (2025)
- [AutoPentester: An LLM Agent-based Framework for Automated Pentesting](https://mlsanity.com/paper/2510.05605/) (2025)
- [An Investigation of Patch Porting Practices of the Linux Kernel Ecosystem](https://mlsanity.com/paper/2402.05212/) (2024)
- [SyzScope: Revealing High-Risk Security Impacts of Fuzzer-Exposed Bugs in Linux kernel](https://mlsanity.com/paper/2111.06002/) (2021)
- [PBFuzz: Agentic Directed Fuzzing for PoV Generation](https://mlsanity.com/paper/2512.04611/) (2025)
- [Your Fix Is My Exploit: Enabling Comprehensive DL Library API Fuzzing with Large Language Models](https://mlsanity.com/paper/2501.04312/) (2025)
- [ProphetFuzz: Fully Automated Prediction and Fuzzing of High-Risk Option Combinations with Only Documentation via Large Language Model](https://mlsanity.com/paper/2409.00922/) (2024)
- [Top of the Heap: Efficient Memory Error Protection of Safe Heap Objects](https://mlsanity.com/paper/2310.06397/) (2023)

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

- [ExploitBench: A Capability Ladder Benchmark for LLM Cybersecurity Agents](https://mlsanity.com/paper/2605.14153/) (2026)
- [SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?](https://mlsanity.com/paper/2605.26548/) (2026)
- [PoC-Adapt: Semantic-Aware Automated Vulnerability Reproduction with LLM Multi-Agents and Reinforcement Learning-Driven Adaptive Policy](https://mlsanity.com/paper/2604.06618/) (2026)
- [The Next Challenge for Agentic Cybersecurity: A Realistic, Contamination-Free Reverse Engineering Benchmark](https://mlsanity.com/paper/2608.11469/) (2026)
- [Benchmarking Automated Security Patch Backporting: How Far Are We?](https://mlsanity.com/paper/2608.17671/) (2026)
- [PrimSynth: An Agentic Approach to Discover, Validate, and Synthesize Exploit Primitives for Linux Kernel Vulnerabilities](https://mlsanity.com/paper/2609.02647/) (2026)
- [The History Is the Detector: Executing CVE Patch History, End-to-End](https://mlsanity.com/paper/2609.05335/) (2026)

## Abstract (arXiv)

Autonomous large language model (LLM) based systems have recently shown promising results across a range of cybersecurity tasks. However, there is no systematic study on their effectiveness in autonomously reproducing Linux kernel vulnerabilities with concrete proofs-of-concept (PoCs). Owing to the size, complexity, and low-level nature of the Linux kernel, such tasks are widely regarded as particularly challenging for current LLM-based approaches. In this paper, we present the first large-scale study of LLM-based Linux kernel vulnerability reproduction. For this purpose, we develop K-Repro, an LLM-based agentic system equipped with controlled code-browsing, virtual machine management, interaction, and debugging capabilities. Using kernel security patches as input, K-Repro automates end-to-end bug reproduction of N-day vulnerabilities in the Linux kernel. On a dataset of 100 real-world exploitable Linux kernel vulnerabilities collected from KernelCTF, our results show that K-Repro can generate PoCs that reproduce over 50% of the cases with practical time and monetary cost. Beyond aggregate success rates, we perform an extensive study of effectiveness, efficiency, stability, and impact factors to explain when agentic reproduction succeeds, where it fails, and which components drive performance. These findings provide actionable guidance for building more reliable autonomous security agents and for assessing real-world N-day risk from both offensive and defensive perspectives.