用大模型持续进化符号解法，让机器像人一样不断发现新科学规律。
CoEvo: Continual Evolution of Symbolic Solutions Using Large Language Models
- 结合大模型与演化算法，动态生成并优化数学表达式和逻辑规则。
- 在多个任务上实现更高搜索效率，支持开放式的持续创新。
- 适合科研自动化、AI科学家方向的研究者和开发者。
符号解法的发现——如数学公式、逻辑规则和算法结构——是推动科学与工程进步的核心。然而，传统方法常面临搜索效率低和知识整合不足的问题。尽管基于大语言模型（LLM）的新方法提升了搜索效率，却缺乏对已发现解法及其知识的持续优化能力，限制了其在开放式创新中的潜力。为此，我们提出CoEvo框架，利用大语言模型在演化搜索过程中持续生成并改进符号解法。CoEvo引入动态知识库，通过自然语言、数学表达式和代码等多种表示形式，实现高效的知识管理与探索。该方法融合大模型的推理能力与演化算法的探索性，显著提升符号发现的效率与范围。实验表明，CoEvo不仅加速了符号解法的搜索过程，还能支持持续发现，类比于人类科学探索的长期迭代。本研究首次将符号解法搜索构想为终身、迭代的过程，标志着大语言模型在科学突破持续追求中迈出关键一步。代码开源：https://github.com/pgg3/CoEvo。
原文摘要 · Abstract (English)
The discovery of symbolic solutions -- mathematical expressions, logical rules, and algorithmic structures -- is fundamental to advancing scientific and engineering progress. However, traditional methods often struggle with search efficiency and fail to integrate knowledge effectively. While recent large language model-based (LLM-based) approaches have demonstrated improvements in search efficiency, they lack the ability to continually refine and expand upon discovered solutions and their underlying knowledge, limiting their potential for open-ended innovation. To address these limitations, we introduce CoEvo, a novel framework that leverages large language models within an evolutionary search methodology to continually generate and refine symbolic solutions. CoEvo integrates a dynamic knowledge library, enabling open-ended innovation of solutions through effective knowledge management. Additionally, CoEvo leverages multiple representations of solutions -- including natural language, mathematical expressions, and code -- to further enhance search efficiency. By combining the reasoning capabilities of LLMs with the exploratory power of evolutionary algorithms, CoEvo significantly improves the efficiency and scope of symbolic discovery. Our experimental results demonstrate that this method not only enhances the efficiency of searching for symbolic solutions but also supports the ongoing discovery process, akin to human scientific endeavors. This study represents a first effort in conceptualizing the search for symbolic solutions as a lifelong, iterative process, marking a significant step towards harnessing LLMs in the perpetual pursuit of scientific and engineering breakthroughs. Our code is available at https://github.com/pgg3/CoEvo.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。