PlanGenLLMs: A Modern Survey of LLM Planning Capabilities

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wei, Hui, Zhang, Zihao, He, Shenghua, Xia, Tian, Pan, Shijia, Liu, Fei
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916804714037248
author Wei, Hui
Zhang, Zihao
He, Shenghua
Xia, Tian
Pan, Shijia
Liu, Fei
author_facet Wei, Hui
Zhang, Zihao
He, Shenghua
Xia, Tian
Pan, Shijia
Liu, Fei
contents LLMs have immense potential for generating plans, transforming an initial world state into a desired goal state. A large body of research has explored the use of LLMs for various planning tasks, from web navigation to travel planning and database querying. However, many of these systems are tailored to specific problems, making it challenging to compare them or determine the best approach for new tasks. There is also a lack of clear and consistent evaluation criteria. Our survey aims to offer a comprehensive overview of current LLM planners to fill this gap. It builds on foundational work by Kartam and Wilkins (1990) and examines six key performance criteria: completeness, executability, optimality, representation, generalization, and efficiency. For each, we provide a thorough analysis of representative works and highlight their strengths and weaknesses. Our paper also identifies crucial future directions, making it a valuable resource for both practitioners and newcomers interested in leveraging LLM planning to support agentic workflows.
format Preprint
id arxiv_https___arxiv_org_abs_2502_11221
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PlanGenLLMs: A Modern Survey of LLM Planning Capabilities
Wei, Hui
Zhang, Zihao
He, Shenghua
Xia, Tian
Pan, Shijia
Liu, Fei
Artificial Intelligence
Computation and Language
LLMs have immense potential for generating plans, transforming an initial world state into a desired goal state. A large body of research has explored the use of LLMs for various planning tasks, from web navigation to travel planning and database querying. However, many of these systems are tailored to specific problems, making it challenging to compare them or determine the best approach for new tasks. There is also a lack of clear and consistent evaluation criteria. Our survey aims to offer a comprehensive overview of current LLM planners to fill this gap. It builds on foundational work by Kartam and Wilkins (1990) and examines six key performance criteria: completeness, executability, optimality, representation, generalization, and efficiency. For each, we provide a thorough analysis of representative works and highlight their strengths and weaknesses. Our paper also identifies crucial future directions, making it a valuable resource for both practitioners and newcomers interested in leveraging LLM planning to support agentic workflows.
title PlanGenLLMs: A Modern Survey of LLM Planning Capabilities
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2502.11221