📄 中文摘要
SkyDiscover 是一个开源的模块化框架，旨在推动 AI 驱动的算法发现。与以往的封闭源系统（如 AlphaEvolve）不同，SkyDiscover 提供了开放的实现，解决了现有单体系统难以扩展的问题。该框架将发现循环分解为多个模块，使得用户能够更灵活地进行算法探索和优化。通过这种方式，SkyDiscover 促进了算法发现的透明性和可扩展性，为研究人员和开发者提供了更强大的工具。该项目的开源发布将有助于推动相关领域的进一步发展。
SkyDiscover：一个基于大语言模型的算法发现开放框架
出处: SkyDiscover: An Open Framework for LLM-Driven Algorithm Discovery
发布: 2026年3月3日
📄 English Summary
SkyDiscover: An Open Framework for LLM-Driven Algorithm Discovery
SkyDiscover is an open-source modular framework designed to facilitate AI-driven algorithm discovery. Unlike previous closed-source systems such as AlphaEvolve, SkyDiscover offers an open implementation that addresses the challenges of existing monolithic systems that are difficult to extend. The framework decomposes the discovery loop into multiple modules, allowing users to explore and optimize algorithms more flexibly. This approach enhances the transparency and scalability of algorithm discovery, providing researchers and developers with more powerful tools. The open-source release of this project is expected to contribute to further advancements in the field.