CodeEvolve: LLM-Driven Evolutionary Optimization with Runtime-Enriched Target Selection for Multi-Language Code Enhancement
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917463632904192 |
|---|---|
| author | Borra, Ajay Krishna Yang, Wenzhuo Arora, Samarth Gotmare, Akhilesh Deepak Gopalakrishnan, Gokulakrishnan Gali, Tharun Rathi, Madhav Sahoo, Doyen Singh, Manpreet Verma, Mayuresh Venka, Laksh Singh, Shuchita |
| author_facet | Borra, Ajay Krishna Yang, Wenzhuo Arora, Samarth Gotmare, Akhilesh Deepak Gopalakrishnan, Gokulakrishnan Gali, Tharun Rathi, Madhav Sahoo, Doyen Singh, Manpreet Verma, Mayuresh Venka, Laksh Singh, Shuchita |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_04677 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CodeEvolve: LLM-Driven Evolutionary Optimization with Runtime-Enriched Target Selection for Multi-Language Code Enhancement Borra, Ajay Krishna Yang, Wenzhuo Arora, Samarth Gotmare, Akhilesh Deepak Gopalakrishnan, Gokulakrishnan Gali, Tharun Rathi, Madhav Sahoo, Doyen Singh, Manpreet Verma, Mayuresh Venka, Laksh Singh, Shuchita Software Engineering Artificial Intelligence I.2.2; I.2.5 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. |
| title | CodeEvolve: LLM-Driven Evolutionary Optimization with Runtime-Enriched Target Selection for Multi-Language Code Enhancement |
| topic | Software Engineering Artificial Intelligence I.2.2; I.2.5 |
| url | https://arxiv.org/abs/2605.04677 |