2 个仓库
Awesome GitHub RepositoriesEvolutionary Algorithm Discovery
Automated discovery and refinement of optimization algorithms through iterative mutation and selection.
Distinct from Heuristic Optimization Algorithms: Distinct from Heuristic Optimization Algorithms: focuses on evolving the algorithm itself via code mutation, not on applying known heuristics.
Explore 2 awesome GitHub repositories matching artificial intelligence & ml · Evolutionary Algorithm Discovery. Refine with filters or upvote what's useful.
Awesome Evolutionary Algorithm Discovery GitHub Repositories
用 AI 发现最棒的仓库。我们将通过 AI 为您搜索最匹配的仓库。
- codelion/openevolve
codelion/openevolve
6,608在 GitHub 上查看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。
Implements an evolutionary pipeline using LLMs to autonomously discover and optimize efficient algorithms.
Python - algorithmicsuperintelligence/openevolve
algorithmicsuperintelligence/openevolve
5,421在 GitHub 上查看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
Evo transforms a basic random search into advanced algorithms like simulated annealing through iterative code mutation and performance evaluation.
Pythonalpha-evolvealphacodealphaevolve
