# AutoPatch: Multi-Agent Framework for Patching Real-World CVE Vulnerabilities

arXiv: https://arxiv.org/abs/2505.04195 · HTML: https://mlsanity.com/paper/2505.04195/

## Key facts

- Cited by 4 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 19 of its 53 references that are in the map.
- First posted on arXiv 7 May 2025.

## 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, 19 of 19)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence](https://mlsanity.com/paper/2406.11931/) (2024)
- [Faithful Chain-of-Thought Reasoning](https://mlsanity.com/paper/2301.13379/) (2023)
- [Vulnerability Detection with Code Language Models: How Far Are We?](https://mlsanity.com/paper/2403.18624/) (2024)
- [LLMs Cannot Reliably Identify and Reason About Security Vulnerabilities (Yet?): A Comprehensive Evaluation, Framework, and Benchmarks](https://mlsanity.com/paper/2312.12575/) (2023)
- [Vul-RAG: Enhancing LLM-based Vulnerability Detection via Knowledge-level RAG](https://mlsanity.com/paper/2406.11147/) (2024)
- [Understanding the Effectiveness of Large Language Models in Detecting Security Vulnerabilities](https://mlsanity.com/paper/2311.16169/) (2023)
- [LLMs in Software Security: A Survey of Vulnerability Detection Techniques and Insights](https://mlsanity.com/paper/2502.07049/) (2025)
- [Chain-of-Thought Prompting of Large Language Models for Discovering and Fixing Software Vulnerabilities](https://mlsanity.com/paper/2402.17230/) (2024)
- [ThinkRepair: Self-Directed Automated Program Repair](https://mlsanity.com/paper/2407.20898/) (2024)
- [VulDetectBench: Evaluating the Deep Capability of Vulnerability Detection with Large Language Models](https://mlsanity.com/paper/2406.07595/) (2024)
- [CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance](https://mlsanity.com/paper/2502.04350/) (2025)
- [STEAM: Simulating the InTeractive BEhavior of ProgrAMmers for Automatic Bug Fixing](https://mlsanity.com/paper/2308.14460/) (2023)
- [Multitask Mayhem: Unveiling and Mitigating Safety Gaps in LLMs Fine-tuning](https://mlsanity.com/paper/2409.15361/) (2024)
- [LProtector: An LLM-driven Vulnerability Detection System](https://mlsanity.com/paper/2411.06493/) (2024)
- [Fight Fire with Fire: How Much Can We Trust ChatGPT on Source Code-Related Tasks?](https://mlsanity.com/paper/2405.12641/) (2024)
- [RESTORE: Retrospective Fault Localization Enhancing Automated Program Repair](https://mlsanity.com/paper/1906.01778/) (2019)

## Built on by (most cited first, 4 of 4)

- [Core-based Hierarchies for Efficient GraphRAG](https://mlsanity.com/paper/2603.05207/) (2026)
- [SoK: Measuring What Matters for Closed-Loop Security Agents](https://mlsanity.com/paper/2510.01654/) (2025)
- [Verify Before You Fix: Agentic Execution Grounding for Trustworthy Cross-Language Code Analysis](https://mlsanity.com/paper/2604.10800/) (2026)
- [FirmPilot: Evidence-Guided Multi-Agent Environment Recovery for IoT Firmware Rehosting](https://mlsanity.com/paper/2607.14903/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have emerged as promising tools in software development, enabling automated code generation and analysis. However, their knowledge is limited to a fixed cutoff date, making them prone to generating code vulnerable to newly disclosed CVEs. Frequent fine-tuning with new CVE sets is costly, and existing LLM-based approaches focus on oversimplified CWE examples and require providing explicit bug locations to LLMs, limiting their ability to patch complex real-world vulnerabilities. To address these limitations, we propose AutoPatch, a multi-agent framework designed to patch vulnerable LLM-generated code, particularly those introduced after the LLMs' knowledge cutoff. AutoPatch integrates Retrieval-Augmented Generation (RAG) with a structured database of recently disclosed vulnerabilities, comprising 525 code snippets derived from 75 high-severity CVEs across real-world systems such as the Linux kernel and Chrome. AutoPatch combines semantic and taint analysis to identify the most relevant CVE and leverages enhanced Chain-of-Thought (CoT) reasoning to construct enriched prompts for verification and patching. Our unified similarity model, which selects the most relevant vulnerabilities, achieves 90.4 percent accuracy in CVE matching. AutoPatch attains 89.5 percent F1-score for vulnerability verification and 95.0 percent accuracy in patching, while being over 50x more cost-efficient than traditional fine-tuning approaches.