CodeEvolve: LLM-Driven Evolutionary Optimization with Runtime-Enriched Target Selection for Multi-Language Code Enhancement

TL;DR

CodeEvolve is an LLM-driven evolutionary framework that enhances multi-language code performance and quality by runtime-guided target selection, automated refinement, and systematic evaluation, achieving significant speedups.

Contribution

It introduces a novel runtime-enriched, MCTS-guided optimization process for multi-language code improvement using LLMs, reducing manual bottleneck identification.

Findings

Achieves an average 15.22× speedup on a large Java codebase.

Outperforms single-pass LLM optimization on five out of seven functions.

Full MCTS configuration yields high validity in generated programs.

Abstract

We present CodeEvolve, an evolutionary framework for improving program performance and code quality with Large Language Models (LLMs). CodeEvolve extends OpenEvolve with runtime-guided target selection, Monte Carlo Tree Search (MCTS), automated code refinement, and language-specific evaluation pipelines for Java and Salesforce Apex. The system uses Java Flight Recorder (JFR) profiles to build weighted component graphs and select optimization targets that account for most execution cost, reducing reliance on manual bottleneck identification. For each target, CodeEvolve generates candidate edits, evaluates them through build validation, unit tests, performance checks, static analysis, and LLM-based review, and retains only variants that preserve functional correctness. Across real-world optimization tasks, CodeEvolve improves performance and code metrics while maintaining correctness. On a large enterprise Java codebase, it achieves an average speedup of 15.22$\times$ across seven hotspot functions and outperforms single-pass LLM optimization on five of them. An ablation study on Apex optimization shows that the full MCTS-augmented configuration produces 19.5 valid programs out of 20 on average, indicating that search, filtering, and refinement each contribute to more reliable optimization.