AI-Guided Exploration of Large-Scale Codebases

TL;DR

This paper presents a hybrid system combining reverse engineering and large language models to improve interactive code exploration and comprehension of large-scale software systems.

Contribution

It introduces an integrated approach that merges UML visualization, LLM guidance, and user interaction analysis for enhanced code understanding.

Findings

Prototype for Java demonstrates feasibility

LLM-guided exploration improves navigation

Integrates visualization with intent-aware querying

Abstract

Understanding large-scale, complex software systems is a major challenge for developers, who spend a significant portion of their time on program comprehension. Traditional tools such as static visualizations and reverse engineering techniques provide structural insights but often lack interactivity, adaptability, and integration with contextual information. Recent advancements in large language models (LLMs) offer new opportunities to enhance code exploration workflows, yet their lack of grounding and integration with structured views limits their effectiveness. This work introduces a hybrid approach that integrates deterministic reverse engineering with LLM-guided, intent-aware visual exploration. The proposed system combines UML-based visualization, dynamic user interfaces, historical context, and collaborative features into an adaptive tool for code comprehension. By interpreting user queries and interaction patterns, the LLM helps developers navigate and understand complex codebases more effectively. A prototype implementation for Java demonstrates the feasibility of this approach. Future work includes empirical evaluation, scaling to polyglot systems, and exploring GUI-driven LLM interaction models. This research lays the groundwork for intelligent, interactive environments that align with developer cognition and collaborative workflows.