SoK: AI-Augmented Binary Reversing

The paper presents a comprehensive systematization of knowledge on AI-augmented binary reversing, analyzing 144 research papers from 2015 onward and organizing them into 22 domains based on inference tasks. It introduces a unified taxonomy that connects traditional and AI-driven methodologies, elucidating the roles of large language models (LLMs) and agentic AI systems, while identifying common challenges and opportunities for future research. This framework aims to enhance the reliability and scalability of AI-augmented binary reversing systems, which is crucial for practitioners involved in software analysis and security.