Code for Machines, Not Just Humans: Quantifying AI-Friendliness with Code Health Metrics

2026-01-05

arXiv.org

AI Summary

This study addresses the critical challenge of quantifying how AI-friendly code is for reliable human-AI collaborative software development. By conducting large language model–driven refactoring experiments on 5,000 Python competitive programming files, the work provides the first empirical evidence that CodeHealth—a metric originally designed to assess human readability—effectively predicts the semantic preservation capability of AI-generated edits. The results demonstrate that code with higher CodeHealth scores is significantly more likely to retain semantic correctness after AI-driven refactoring. This finding reveals that enhancing code maintainability can substantially reduce the risk of semantic corruption during AI intervention, thereby offering both a theoretical foundation and practical guidance for developing AI-friendly code through quantifiable means.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Humans and AI: Other Foundations of Human Computation & AI
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

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 is increasingly important to ensure that LLMs with different capabilities can edit code reliably. In this study, we investigate the concept of ``AI-friendly code''via LLM-based refactoring on a dataset of 5,000 Python files from competitive programming. We find a meaningful association between CodeHealth, a quality metric calibrated for human comprehension, and semantic preservation after AI refactoring. Our findings confirm that human-friendly code is also more compatible with AI tooling. These results suggest that organizations can use CodeHealth to guide where AI interventions are lower risk and where additional human oversight is warranted. Investing in maintainability not only helps humans; it also prepares for large-scale AI adoption.

Problem

• AI-friendly code
• CodeHealth
• LLM-based refactoring
• code maintainability
• semantic preservation

Innovation

• AI-friendly code
• CodeHealth
• LLM-based refactoring
• semantic preservation
• code maintainability