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

arXiv:2510.14150 · cs.AI, cs.LG, cs.NE · Submitted 2025-10-15 · Read on arXiv

cs.AI, cs.LG, cs.NE

Submitted: 2025-10-15

Updated: 2026-08-27

Comments: EMNLP 2026 Findings;23 pages, 16 figures, 12 tables

Code: https://github.com/inter-co/science-codeevolve

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 42× in this paper · explained in 2 episodes
• Ablation — 37× in this paper · explained in 1 episode
• Adaptation — 4× in this paper · explained in 1 episode
• Core — 4× in this paper · explained in 2 episodes
• Traveling Salesman Problem — 4× in this paper
• Ablation Studies — 3× in this paper · explained in 1 episode
• Adam — 3× in this paper · explained in 2 episodes
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Evolution of Heuristics — 2× in this paper
• Flow Shop Scheduling Problem — 2× in this paper
• Online Bin Packing Problem — 2× in this paper
• Sample Efficiency — 2× in this paper · explained in 6 episodes
• Scaling Laws — 2× in this paper · explained in 4 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Agentic AI — 1× in this paper · explained in 2 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Hybrid Approach — 1× in this paper · explained in 4 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 8 episodes
• Multi-Agent System — 1× in this paper · explained in 7 episodes
• Objective Function — 1× in this paper · explained in 2 episodes
• Pairwise Comparisons — 1× in this paper · explained in 2 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Quantization — 1× in this paper · explained in 13 episodes
• Scaffolding — 1× in this paper · explained in 3 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
• How Susceptible are LLMs to Influence in Prompts?
• Small Language Models are the Future of Agentic AI
• Evaluating Large Language Models Trained on Code
• Barbarians at the Gate: How AI is Upending Systems Research
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• Mathematical exploration and discovery at scale
• EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers
• Improved bounds on the supremum of autoconvolutions
• Illuminating search spaces by mapping elites
• ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution
• Optimizing PyTorch Inference with LLM-Based Multi-Agent Systems
• AlphaEvolve: A coding agent for scientific and algorithmic discovery
• Prompt Repetition Improves Non-Reasoning LLMs
• Can Language Models Discover Scaling Laws?
• EoH-S: Evolution of Heuristic Set using LLMs for Automated Heuristic Design
• gpt-oss-120b & gpt-oss-20b Model Card
• GPT-4 Technical Report
• Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding
• Using Centroidal Voronoi Tessellations to Scale Up the Multi-dimensional Archive of Phenotypic Elites Algorithm

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems