An LLM-Based Agent-Oriented Approach for Automated Code Design Issue Localization
Authors:
- 26 April 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1320-1332
Abstract
Maintaining software design quality is crucial for the long-term maintainability and evolution of systems. However, design issues such as poor modularity and excessive complexity often emerge as codebases grow. Developers rely on external tools, such as program analysis techniques, to identify such issues. This work leverages Large Language Models (LLMs) to develop an automated approach for analyzing and localizing design issues. Large language models have demonstrated significant performance on coding tasks, but directly leveraging them for design issue localization is challenging. Large codebases exceed typical LLM context windows, and program analysis tool outputs in non-textual modalities (e.g., graphs or interactive visualizations) are incompatible with LLMs' natural language inputs. To address these challenges, we propose LOCALIZEAGENT, a novel multi-agent framework for effective design issue localization. LOCALIZEAGENT integrates the specialized agents that (1) analyze code to identify potential code design issues, (2) transform program analysis outputs into abstraction-aware LLM-friendly natural language summaries, (3) generate context-aware prompts tailored to specific refactoring types, and (4) leverage LLMs to locate and rank the localized issues based on their relevance. Our evaluation using diverse real-world codebases demonstrates significant improvements over the baseline approaches, with LOCALIZEAGENT achieving $138 \%, 166 \%$, and 206 % relative improvements in exact-match accuracy for localizing information hiding, complexity, and modularity issues, respectively.
Keywords
Funding Information
- National Science Foundation (25-12857,25-12858,15-18897,15-13263,21-20448,19-34884,22-23812)
This publication has 20 references indexed in Scilit:
- RepairAgent: An Autonomous, LLM-Based Agent for Program Repair2025
- Large Language Models are Few-Shot Summarizers: Multi-Intent Comment Generation via In-Context Learning2024
- Refactoring Programs Using Large Language Models with Few-Shot Examples2023
- NatGen: generative pre-training by “naturalizing” source code2022
- The Effectiveness of Supervised Machine Learning Algorithms in Predicting Software RefactoringIEEE Transactions on Software Engineering, 2020
- Accurate and efficient refactoring detection in commit history2018
- The financial aspect of managing technical debt: A systematic literature reviewInformation and Software Technology, 2015
- Measuring architecture quality by structure plus history analysis2013
- Managing technical debt in software-reliant systems2010
- Iterative identification of fault-prone binaries using in-process metrics2008