Tuning LLM-based Code Optimization via Meta-Prompting: An Industrial Perspective

TL;DR

This paper presents MPCO, a meta-prompting framework that automatically generates effective prompts for multiple LLMs to optimize code, overcoming prompt engineering challenges in industrial multi-LLM systems.

Contribution

We introduce MPCO, a novel meta-prompting approach that dynamically creates task-specific prompts for diverse LLMs, enhancing code optimization in industrial settings.

Findings

Achieves up to 19.06% performance improvement.

96% of top optimizations are meaningful edits.

Effective context integration is crucial for success.

Abstract

There is a growing interest in leveraging multiple large language models (LLMs) for automated code optimization. However, industrial platforms deploying multiple LLMs face a critical challenge: prompts optimized for one LLM often fail with others, requiring expensive model-specific prompt engineering. This cross-model prompt engineering bottleneck severely limits the practical deployment of multi-LLM systems in production environments. We introduce Meta-Prompted Code Optimization (MPCO), a framework that automatically generates high-quality, task-specific prompts across diverse LLMs while maintaining industrial efficiency requirements. MPCO leverages metaprompting to dynamically synthesize context-aware optimization prompts by integrating project metadata, task requirements, and LLM-specific contexts. It is an essential part of the ARTEMIS code optimization platform for automated validation and scaling. Our comprehensive evaluation on five real-world codebases with 366 hours of runtime benchmarking demonstrates MPCO's effectiveness: it achieves overall performance improvements up to 19.06% with the best statistical rank across all systems compared to baseline methods. Analysis shows that 96% of the top-performing optimizations stem from meaningful edits. Through systematic ablation studies and meta-prompter sensitivity analysis, we identify that comprehensive context integration is essential for effective meta-prompting and that major LLMs can serve effectively as meta-prompters, providing actionable insights for industrial practitioners.