A Contemporary Survey of Large Language Model Assisted Program Analysis

TL;DR

This survey reviews how large language models are transforming program analysis by enabling more effective static, dynamic, and hybrid approaches, highlighting recent advances, challenges, and future directions.

Contribution

It provides a comprehensive categorization and synthesis of recent LLM applications in program analysis, addressing a gap in existing cybersecurity-focused surveys.

Findings

LLMs enhance code comprehension and analysis capabilities.

Recent studies show promising results in static, dynamic, and hybrid analysis.

Future challenges include scalability, domain adaptation, and security concerns.

Abstract

The increasing complexity of software systems has driven significant advancements in program analysis, as traditional methods unable to meet the demands of modern software development. To address these limitations, deep learning techniques, particularly Large Language Models (LLMs), have gained attention due to their context-aware capabilities in code comprehension. Recognizing the potential of LLMs, researchers have extensively explored their application in program analysis since their introduction. Despite existing surveys on LLM applications in cybersecurity, comprehensive reviews specifically addressing their role in program analysis remain scarce. In this survey, we systematically review the application of LLMs in program analysis, categorizing the existing work into static analysis, dynamic analysis, and hybrid approaches. Moreover, by examining and synthesizing recent studies, we identify future directions and challenges in the field. This survey aims to demonstrate the potential of LLMs in advancing program analysis practices and offer actionable insights for security researchers seeking to enhance detection frameworks or develop domain-specific models.