AI-Assisted Automated Code Refactoring and Technical Debt Reduction: Supporting Digital Knowledge Documentation and Preservation
TL;DR
This study evaluates whether AI-assisted refactoring prioritization can reduce technical debt more effectively than traditional rule-based static analysis, using cyclomatic complexity, maintainability index, and remediation effort as debt indicators.
Abstract
Technical debt represents a persistent challenge in software engineering, characterized by design decisions that increase long-term maintenance costs and reduce software quality. This study evaluates whether AI-assisted refactoring prioritization can reduce technical debt more effectively than traditional rule-based static analysis, using cyclomatic complexity, maintainability index, and remediation effort as debt indicators. Across a dataset of 120,000 code samples and six real Java source files, AI-assisted prioritization achieves 18%–89% greater cumulative complexity reduction compared to rule-based baselines. Beyond software quality, this work contributes to the emerging field of digital knowledge documentation by demonstrating how intelligent, structured analysis tools can preserve and improve access to complex technical information assets over time.