Saved in:
Bibliographic Details
Main Authors: Puerta-Merino, Israel, Núñez-Molina, Carlos, Mesejo, Pablo, Fernández-Olivares, Juan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.08068
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911281407066112
author Puerta-Merino, Israel
Núñez-Molina, Carlos
Mesejo, Pablo
Fernández-Olivares, Juan
author_facet Puerta-Merino, Israel
Núñez-Molina, Carlos
Mesejo, Pablo
Fernández-Olivares, Juan
contents Recent advances in Large Language Models (LLMs) are fostering their integration into several reasoning-related fields, including Automated Planning (AP). However, their integration into Hierarchical Planning (HP), a subfield of AP that leverages hierarchical knowledge to enhance planning performance, remains largely unexplored. In this preliminary work, we propose a roadmap to address this gap and harness the potential of LLMs for HP. To this end, we present a taxonomy of integration methods, exploring how LLMs can be utilized within the HP life cycle. Additionally, we provide a benchmark with a standardized dataset for evaluating the performance of future LLM-based HP approaches, and present initial results for a state-of-the-art HP planner and LLM planner. As expected, the latter exhibits limited performance (3\% correct plans, and none with a correct hierarchical decomposition) but serves as a valuable baseline for future approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2501_08068
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Roadmap to Guide the Integration of LLMs in Hierarchical Planning
Puerta-Merino, Israel
Núñez-Molina, Carlos
Mesejo, Pablo
Fernández-Olivares, Juan
Artificial Intelligence
Recent advances in Large Language Models (LLMs) are fostering their integration into several reasoning-related fields, including Automated Planning (AP). However, their integration into Hierarchical Planning (HP), a subfield of AP that leverages hierarchical knowledge to enhance planning performance, remains largely unexplored. In this preliminary work, we propose a roadmap to address this gap and harness the potential of LLMs for HP. To this end, we present a taxonomy of integration methods, exploring how LLMs can be utilized within the HP life cycle. Additionally, we provide a benchmark with a standardized dataset for evaluating the performance of future LLM-based HP approaches, and present initial results for a state-of-the-art HP planner and LLM planner. As expected, the latter exhibits limited performance (3\% correct plans, and none with a correct hierarchical decomposition) but serves as a valuable baseline for future approaches.
title A Roadmap to Guide the Integration of LLMs in Hierarchical Planning
topic Artificial Intelligence
url https://arxiv.org/abs/2501.08068