Researchers have developed ARQ, a novel framework that uses Large Language Models (LLMs) to automatically refine CodeQL queries for detecting vulnerabilities in C/C++ programs. This agentic approach leverages execution-grounded evidence from synthesized programs to identify and correct false positives and false negatives in existing queries. ARQ requires no labeled datasets or commit history, demonstrating significant improvements in true positive detection by up to 119.8% while maintaining at least 98.0% precision. The refined queries have also successfully addressed long-standing GitHub issues and uncovered previously unknown bugs in real-world libraries like libpng and zlib. AI
IMPACT Enhances automated code analysis and security by improving the accuracy of vulnerability detection tools.
RANK_REASON The cluster describes a research paper detailing a new framework for improving vulnerability detection using LLMs. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
