# CodeEvolve: an open source evolutionary coding agent for algorithmic discovery and optimization

arXiv: https://arxiv.org/abs/2510.14150 · HTML: https://mlsanity.com/paper/2510.14150/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 17 of its 58 references that are in the map.
- First posted on arXiv 15 Oct 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 17 of 17)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015)
- [ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution](https://mlsanity.com/paper/2402.01145/) (2024)
- [Small Language Models are the Future of Agentic AI](https://mlsanity.com/paper/2506.02153/) (2025)
- [Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model](https://mlsanity.com/paper/2401.02051/) (2024)
- [EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers](https://mlsanity.com/paper/2309.08532/) (2023)
- [ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution](https://mlsanity.com/paper/2509.19349/) (2025)
- [Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding](https://mlsanity.com/paper/2401.12954/) (2024)
- [LLaMEA: A Large Language Model Evolutionary Algorithm for Automatically Generating Metaheuristics](https://mlsanity.com/paper/2405.20132/) (2024)
- [Using Centroidal Voronoi Tessellations to Scale Up the Multi-dimensional Archive of Phenotypic Elites Algorithm](https://mlsanity.com/paper/1610.05729/) (2016)
- [Barbarians at the Gate: How AI is Upending Systems Research](https://mlsanity.com/paper/2510.06189/) (2025)
- [EoH-S: Evolution of Heuristic Set using LLMs for Automated Heuristic Design](https://mlsanity.com/paper/2508.03082/) (2025)
- [How Susceptible are LLMs to Influence in Prompts?](https://mlsanity.com/paper/2408.11865/) (2024)
- [Can Language Models Discover Scaling Laws?](https://mlsanity.com/paper/2507.21184/) (2025)

## Built on by (most cited first, 30 of 44)

- [EvoX: Meta-Evolution for Automated Discovery](https://mlsanity.com/paper/2602.23413/) (2026)
- [Structured Scaling of AI Discovery Across Diverse Scientific Domains](https://mlsanity.com/paper/2604.19341/) (2026)
- [Dream-RSI: Recursive Self-Improvement through Evolving Worlds](https://mlsanity.com/paper/2609.14858/) (2026)
- [MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI](https://mlsanity.com/paper/2605.08678/) (2026)
- [Effective Harness Engineering for Algorithm Discovery with Coding Agents](https://mlsanity.com/paper/2605.15221/) (2026)
- [Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks](https://mlsanity.com/paper/2606.29082/) (2026)
- [SwarmResearch: Orchestrating Coding Agents for Open-Ended Discovery](https://mlsanity.com/paper/2607.02807/) (2026)
- [Automated Discovery Has No Universally Superior Harness](https://mlsanity.com/paper/2607.18235/) (2026)
- [PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents](https://mlsanity.com/paper/2605.07039/) (2026)
- [GEAR: Genetic AutoResearch for Agentic Code Evolution](https://mlsanity.com/paper/2605.13874/) (2026)
- [Compute Allocation for Self-Evolving LLMs: From Depth-Breadth to Multi-Armed Bandits](https://mlsanity.com/paper/2605.29268/) (2026)
- [TurboEvolve: Towards Fast and Robust LLM-Driven Program Evolution](https://mlsanity.com/paper/2604.18607/) (2026)
- [SeaEvo: Advancing Algorithm Discovery with Strategy Space Evolution](https://mlsanity.com/paper/2604.24372/) (2026)
- [FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage Orchestration](https://mlsanity.com/paper/2605.08520/) (2026)
- [What Do Evolutionary Coding Agents Evolve?](https://mlsanity.com/paper/2605.20086/) (2026)
- [Agentic Architect: An Agentic AI Framework for Architecture Design Exploration and Optimization](https://mlsanity.com/paper/2604.25083/) (2026)
- [Open-Ended Task Discovery via Bayesian Optimization](https://mlsanity.com/paper/2605.07572/) (2026)
- [Evolving Ensemble of Agents](https://mlsanity.com/paper/2605.09018/) (2026)
- [Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty](https://mlsanity.com/paper/2606.25198/) (2026)
- [Knowledge-Centric Self-Improvement](https://mlsanity.com/paper/2607.19592/) (2026)
- [Relay, Don't Route: Adaptive Population Handoff for Cost-Efficient LLM-Driven Evolution](https://mlsanity.com/paper/2608.05651/) (2026)
- [Improved Upper Bounds for Slicing the Hypercube](https://mlsanity.com/paper/2602.16807/) (2026)
- [Autopoiesis: A Self-Evolving System Paradigm for LLM Serving Under Runtime Dynamics](https://mlsanity.com/paper/2604.07144/) (2026)
- [From I/O to Code with Discovery Agent](https://mlsanity.com/paper/2605.15334/) (2026)
- [Evolutionary Intelligence for Scientific Discovery: From Evolutionary Computation to Cumulative Discovery Systems](https://mlsanity.com/paper/2607.09025/) (2026)
- [The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Workflows](https://mlsanity.com/paper/2608.06714/) (2026)
- [Stateless Language Agents: Scaling Long-Horizon Automated Research](https://mlsanity.com/paper/2610.07625/) (2026)
- [ParEVO: Synthesizing Code for Irregular Data: High-Performance Parallelism through Agentic Evolution](https://mlsanity.com/paper/2603.02510/) (2026)
- [Evolutionary Search for Automated Design of Uncertainty Quantification Methods](https://mlsanity.com/paper/2604.03473/) (2026)
- [TuxBot: Semantic-Aware Online OS Tuning with Large Language Models](https://mlsanity.com/paper/2605.15026/) (2026)

## Abstract (arXiv)

We introduce CodeEvolve, an open-source framework that couples large language models with island-based evolutionary search for end-to-end algorithmic discovery. CodeEvolve integrates inspiration-based crossover, meta-prompting, and depth-based refinement on top of a CVT-MAP-Elites archive and a weighted LLM ensemble to generate optimized solutions for complex problems. On the AlphaEvolve benchmark suite, CodeEvolve matches or surpasses the reported AlphaEvolve results on 5 of 9 problems and, under matched conditions, outperforms the open-source frameworks OpenEvolve and ShinkaEvolve on 6 of 9. With the open-weight Qwen3-Coder-30B backbone, it surpasses the reported AlphaEvolve score on both CirclePackingSquare instances at roughly an order of magnitude lower cost than a frontier closed-source ensemble, and remains competitive with EoH on heuristic-design tasks without retuning. Ablations show that the interaction between CodeEvolve's components, rather than any single operator, drives these results. We release the framework, experimental data, and practical hyperparameter guidelines at https://github.com/inter-co/science-codeevolve.