arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.12435cs.AIcs.CL
收藏

面向自动化规划的大语言模型综述

A Survey on Large Language Models for Automated Planning

George Mason University(乔治梅森大学)

Mohamed Aghzal, Erion Plaku, Gregory J. Stein, Ziyu Yao

AI总结:

该综述批判性梳理 LLM 在自动化规划中的研究,指出其不宜独立承担规划器,但与传统方法结合可发挥显著价值。

摘要:

近年来,大语言模型(LLM)的规划能力因其出色的多步推理能力以及在众多领域中的泛化能力而受到越来越多的关注。一些研究人员强调 LLM 执行复杂规划任务的潜力,而另一些研究人员则指出其性能存在显著局限,尤其是在这些模型需要处理长程推理的复杂细节时。在本综述中,我们批判性地考察了关于将 LLM 用于自动化规划的现有研究,详细检验了它们的成功与不足。我们表明,尽管由于这些局限,LLM 并不适合作为独立规划器,但当它们与其他方法相结合时,仍为增强规划应用提供了巨大机遇。因此,我们倡导一种平衡的方法论,即在利用 LLM 固有的灵活性和通用知识的同时,结合传统规划方法的严谨性与成本效益。

英文摘要:

The planning ability of Large Language Models (LLMs) has garnered increasing attention in recent years due to their remarkable capacity for multi-step reasoning and their ability to generalize across a wide range of domains. While some researchers emphasize the potential of LLMs to perform complex planning tasks, others highlight significant limitations in their performance, particularly when these models are tasked with handling the intricacies of long-horizon reasoning. In this survey, we critically investigate existing research on the use of LLMs in automated planning, examining both their successes and shortcomings in detail. We illustrate that although LLMs are not well-suited to serve as standalone planners because of these limitations, they nonetheless present an enormous opportunity to enhance planning applications when combined with other approaches. Thus, we advocate for a balanced methodology that leverages the inherent flexibility and generalized knowledge of LLMs alongside the rigor and cost-effectiveness of traditional planning methods.

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。

↑