arXiv · 2611.19719
Found, but Not Fixed : From Software Vulnerability Discovery to Fixes with Iterative LLM Pipelines
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
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Youssef Gamal, Mohamad Fakih, Halima Bouzidi, Rahul Dharmaji, Gustavo Quiros Araya, Oluwatosin Ogundare, Mst Ayesha Siddika, Mohammad Abdullah Al Faruque. 2026-11-15. Found, but Not Fixed : From Software Vulnerability Discovery to Fixes with Iterative LLM Pipelines. https://searcharxiv.com/abs/2611.19719
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.