2 个仓库
Systems that use evolutionary computation and model generation to iteratively improve source code across languages.
Distinguishing note: Different from general code optimization or specific trading strategies; it is a general-purpose evolutionary optimizer.
Explore 2 awesome GitHub repositories matching artificial intelligence & ml · Evolutionary Code Optimizers. Refine with filters or upvote what's useful.
OpenEvolve 是一个进化算法框架,使用大语言模型来自主发现和优化编程算法。它作为一个算法发现引擎和代码搜索工具,进化候选程序群体以找到高效的实现和特定于硬件的加速。 该系统将代码和系统指令都视为可进化的实体,利用自动提示优化器迭代地改进模型性能。它通过基于生态位的群体管理来保持搜索稳定性以维持多样性,并采用闭环反馈机制,将运行时错误和日志注入回生成过程中以进行自主错误修复。 该框架还包括一个代理编排器,使用加权逻辑和回退策略聚合来自多个模型 API 的响应。为了支持科学计算,它通过管理所有随机组件的一致随机种子来实现确定性执行。 该项目提供了一个用于可视化进化进度和实时性能指标的交互式仪表板。
Uses an LLM-driven evolutionary process to iteratively generate and mutate code for algorithm discovery.
OpenEvolve is an open-source framework for evolutionary computation that uses language models to drive automated optimization across multiple domains. It can evolve system prompts for large language models, refine source code across programming languages, search for optimal GPU kernel configurations, discover interpretable mathematical expressions from data, and maintain diverse populations of high-performing solutions. The framework integrates multiple evolutionary strategies, including MAP-Elites diversity mapping and island-based topologies, to avoid premature convergence and preserve a wid
Using evolutionary algorithms to automatically mutate and select source code variants that improve performance or correctness across multiple programming languages.