Track 3: Automated Code Refactoring
Track 3 focuses on exploring and evaluating the potential of LLM-based automated refactoring of codebases with the ultimate goal of reducing software complexity and improving code quality. We will investigate how LLMs can support and automate tasks such as enhancing maintainability and performance while also reducing technical debt and facilitating bug detection and bug fixing. The main modules include (1) capturing practitioners’ experiences and expectations to establish a roadmap, (2) developing models and benchmarks for LLM-based refactoring, (3) designing autonomous agents, and (4) conducting studies to analyze real-world impact.
Track Leaders TU Delft
Scientific Director, Track Lead
Track Lead
Track Leaders Meta
Track Lead
Director, Track Lead
