arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.14716cs.LGcs.AIcs.CL
收藏

大型语言模型在算法设计中的系统性调研

A Systematic Survey on Large Language Models for Algorithm Design

City University of Hong Kong(香港城市大学);Huawei Noah’s Ark Lab(华为诺亚实验室);Xi'an Jiaotong University(西安交通大学);Huawei Cloud EI Service Product Dept.(华为云EI服务产品部);Southern University of Science(南方科技大学)

Fei Liu, Yiming Yao, Ping Guo, Zhiyuan Yang, Zhe Zhao, Xi Lin, Xialiang Tong, Kun Mao, Zhichao Lu, Zhenkun Wang, Mingxuan Yuan, Qingfu Zhang

AI总结:

本文系统性地综述了大型语言模型在算法设计中的应用,提出分类法分析其角色并指出未来研究方向。

摘要:

算法设计对于在各种领域中有效解决问题至关重要。大型语言模型(LLMs)的出现显著增强了该领域的自动化和创新,提供了新的视角和有希望的解决方案。在短短几年内,这种整合在从组合优化到科学发现的各个领域都取得了显著进展。尽管这种快速扩展,但对该领域的全面理解受到缺乏系统性综述的阻碍,因为现有的综述要么局限于狭窄的子领域,要么具有不同的目标。本文旨在提供一个关于使用LLMs进行算法设计的系统性综述。我们引入了一个分类法,将LLMs的角色分类为优化器、预测器、提取器和设计师,分析每个类别中的进展、优势和局限性。我们进一步综合了算法设计流水线的三个阶段以及定义当前景观的不同算法应用的文献。最后,我们概述了关键的开放挑战和机会,以指导未来的研究。为了支持未来的研究和合作,我们提供了一个配套的存储库:https://github.com/FeiLiu36/LLM4AlgorithmDesign。

英文摘要:

Algorithm design is crucial for effective problem-solving across various domains. The advent of Large Language Models (LLMs) has notably enhanced the automation and innovation within this field, offering new perspectives and promising solutions. In just a few years, this integration has yielded remarkable progress in areas ranging from combinatorial optimization to scientific discovery. Despite this rapid expansion, a holistic understanding of the field is hindered by the lack of a systematic review, as existing surveys either remain limited to narrow sub-fields or with different objectives. This paper seeks to provide a systematic review of algorithm design with LLMs. We introduce a taxonomy that categorises the roles of LLMs as optimizers, predictors, extractors and designers, analyzing the progress, advantages, and limitations within each category. We further synthesize literature across the three phases of the algorithm design pipeline and across diverse algorithmic applications that define the current landscape. Finally, we outline key open challenges and opportunities to guide future research. To support future research and collaboration, we provide an accompanying repository at: https://github.com/FeiLiu36/LLM4AlgorithmDesign.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑