Search papers, labs, and topics across Lattice.
CodeEvolve is an evolutionary optimization framework that leverages LLMs to improve program performance and code quality in Java and Apex. It uses runtime profiling via Java Flight Recorder to identify optimization targets, and Monte Carlo Tree Search to explore candidate code edits generated by the LLM. Experiments on a large Java codebase demonstrate an average speedup of 15.22x across hotspot functions, outperforming single-pass LLM optimization in most cases, while ablation studies highlight the benefits of MCTS and refinement steps.
LLM-guided code evolution, when combined with runtime feedback and MCTS, can reliably achieve 15x speedups on real-world Java code, surpassing naive LLM-based optimization.
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.
