MACEDON : Supporting Programmers with Real-Time Multi-Dimensional Code Evaluation and Optimization

Recent advancements in Large Language Models (LLMs) have led programmers to increasingly turn to them for code optimization and evaluation. However, programmers need to frequently switch between code evaluation and prompt authoring because there is a lack of understanding of the underlying code. Yet, current LLMdriven code assistants do not provide sufficient transparency to help programmers track their code based on the intended evaluation metrics, a crucial step before aligning these evaluations with their optimization goals. To address this gap, we adopted an iterative, user-centered design process by first conducting a formative study and a large-scale code analysis. Based on the findings, we then developed MACEDON, a system that supports multi-dimensional code evaluation in real time, direct code segment optimization, as well as shareable report displays. We evaluated MACEDON through a controlled lab study with 24 novice programmers and two realworld case studies. The results show that MACEDON significantly improved users' ability to identify code issues, apply effective optimizations, and understand their code's evolving state. Our findings suggest that multi-dimensional evaluation, combined with interactive, segment-specific guidance, empowers users to perform more structured and confident code optimization. The code for this paper can be found in https://github.com/xuyeliu/MACEDON.