cs.SENov 15, 2026

Found, but Not Fixed : From Software Vulnerability Discovery to Fixes with Iterative LLM Pipelines

Authors: Youssef Gamal, Mohamad Fakih, Halima Bouzidi, Rahul Dharmaji, Gustavo Quiros Araya, Oluwatosin Ogundare, Mst Ayesha Siddika, Mohammad Abdullah Al Faruque

Organizations: University of California, Irvine, Dept. of Electrical Engineering and Computer Science Irvine, CA, USA · Siemens Technology, Princeton, NJ, USA · Jahangirnagar University, Dept. of Computer Science and Engineering Dhaka, Bangladesh

Abstract

Software vulnerabilities persist as a critical threat despite the deployment of sophisticated detection tools and AI assistants. While detection has advanced, the subsequent code repair phase remains a primary bottleneck; manual intervention is inherently slow, costly, and prone to introducing secondary regressions and issues. In this paper, we investigate whether an iterative, LLM-based pipeline can provide a robust solution for the automated repair of vulnerable functions in real-world code. We propose a generalized framework that leverages the reasoning capabilities of Large Language Models (LLMs) through a multi-stage feedback loop. We benchmark this approach against state-of-the-art models, including GPT-4o, GPT-5.1, and Gemini 3 Flash, demonstrating that such a pipeline can achieve high-quality code repair. To support the broader security community, we provide our evaluation framework, fine-tuned weights, and comprehensive experimental dataset on our website: https://sites.google.com/view/llm4cve

Figures & tables

Explore similar work

CardsList
  1. Metrics Failure in LLM-Based Code Vulnerability Repair: An Empirical Study and a Change-Aware Screen

    Sep 22, 2026Om Nepal, Sushant Aryal, Oluseyi Olukola +1Automated Program RepairLLMs for Cybersecurity

  2. RAVEN: Agentic RAG for Automated Vulnerability Repair

    Jun 21, 2026Varun Gadey, Zijie Liu, Alexandra DmitrienkoRetrieval-Augmented GenerationAutomated Program Repair