5 papers
Code Health in LLM-Based Test Generation: Effectiveness and Token Efficiency
Freya Wirdemann, Markus Borg, Nadim Hagatulah +1
Coding agents powered by Large Language Models (LLMs) are now prominent in software engineering. Previous work has shown that AI tools perform better on high-quality source code th…
Code for Machines, Not Just Humans: Quantifying AI-Friendliness with Code Health Metrics
Markus Borg, Nadim Hagatulah, Adam Tornhill +1
We are entering a hybrid era in which human developers and AI coding agents work in the same codebases. While industry practice has long optimized code for human comprehension, it…
QUPER-MAn: Benchmark-Guided Target Setting for Maintainability Requirements
Markus Borg, Martin Larsson, Philip Breid +1
Maintainable source code is essential for sustainable development in any software organization. Unfortunately, many studies show that maintainability often receives less attention…
ACE: Automated Technical Debt Remediation with Validated Large Language Model Refactorings
Adam Tornhill, Markus Borg, Nadim Hagatulah +1
The remarkable advances in AI and Large Language Models (LLMs) have enabled machines to write code, accelerating the growth of software systems. However, the bottleneck in software…
Echoes of AI: Investigating the Downstream Effects of AI Assistants on Software Maintainability
Markus Borg, Dave Hewett, Nadim Hagatulah +5
[Context] AI assistants, like GitHub Copilot and Cursor, are transforming software engineering. While several studies highlight productivity improvements, their impact on maintaina…