SoK: AI-Augmented Binary Reversing

2026-06-15

AI Summary

Binary reverse engineering remains highly challenging due to the irreversible loss of semantic information caused by compilation, and existing AI-augmented approaches lack a unified framework. This work presents a systematic survey of 144 studies published since 2015, establishing the first comprehensive taxonomy that integrates both traditional and AI-enhanced methods across 22 distinct reverse engineering tasks. We synthesize and analyze techniques in terms of binary representations, learning paradigms, and inference objectives. For the first time, we clarify the roles of large language models and agent-based systems in this domain, introduce a common terminology, and construct a structured knowledge framework that reveals shared architectural patterns among diverse approaches. The study further identifies critical technical bottlenecks and evaluation gaps, laying the foundation for developing reliable and scalable next-generation AI-augmented reverse engineering systems.

Abstract

Binary reversing is fundamental to software understanding, vulnerability discovery, malware investigation, and firmware auditing. However, it remains inherently challenging due to the irreversible loss of semantic information during compilation. Recent advances in machine learning, large language models (LLMs), and agentic AI systems have accelerated the adoption of AI-augmented binary reversing. Yet, the resulting body of work has become increasingly fragmented across reversing domains, artifact representations, learning approaches, and evaluation practices. This paper presents the first comprehensive systematization of knowledge on AI-augmented binary reversing. We analyze 144 research papers published since 2015, and organize them into 22 binary reversing domains according to the inference tasks. We further introduce a unified taxonomy spanning conventional and AI-augmented reversing pipelines. Our taxonomy connects traditional analysis techniques, binary-derived artifacts, representation strategies, learning paradigms, and downstream inference tasks, while clarifying the emerging roles of LLMs and agentic AI systems. By establishing a common vocabulary and structured framework, we provide a holistic view of the field's evolution over the past decade. Our study reveals common structures underlying seemingly disparate approaches, highlights persistent technical challenges and evaluation gaps, and identifies promising opportunities for future research. Collectively, these insights clarify the current state of the field and provide a foundation for the next generation of reliable and scalable AI-augmented binary reversing systems.

Problem

• binary reversing
• AI-augmented
• systematization of knowledge
• fragmentation
• large language models

Innovation

• AI-augmented binary reversing
• systematization of knowledge
• unified taxonomy
• large language models
• agentic AI systems