Large language model-based embodied intelligence task planning: from single-agent to multi-agent

With the development of artificial intelligence, embodied intelligence and task planning have gradually become research hotspots. Traditional task planning methods lack flexibility when facing unpredictable environments, while large language models, with their powerful language understanding and mul...

Full description

Saved in:
Bibliographic Details
Main Authors: JIA Ziqi, WANG Jianzong, ZHANG Xulong, QU Xiaoyang
Format: Article
Language:zho
Published: China InfoCom Media Group 2025-03-01
Series:大数据
Subjects:
Online Access:http://www.j-bigdataresearch.com.cn/thesisDetails#10.11959/j.issn.2096-0271.2025023
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849731664405594112
author JIA Ziqi
WANG Jianzong
ZHANG Xulong
QU Xiaoyang
author_facet JIA Ziqi
WANG Jianzong
ZHANG Xulong
QU Xiaoyang
author_sort JIA Ziqi
collection DOAJ
description With the development of artificial intelligence, embodied intelligence and task planning have gradually become research hotspots. Traditional task planning methods lack flexibility when facing unpredictable environments, while large language models, with their powerful language understanding and multimodal capabilities, provide more comprehensive task planning solutions for intelligent agents, which offers new possibilities for addressing this issue. This paper reviews task planning methods based on large language models, covering different strategies in both single-agent and multi-agent contexts. Several representative frameworks and their performance and potential in practical applications are discussed. Specifically, this paper introduces single-agent large language model task planning methods, such as end-to-end planning, staged planning, and dynamic planning, and multi-agent large language model task planning methods, such as centralized planning, distributed planning, and hybrid planning. It also analyzes how these methods combine with reinforcement learning, multimodal perception, and other techniques to optimize the planning process. In addition, the paper discusses the characteristics, limitations, and challenges of large language model-based embodied intelligence task planning, and outlines the future development directions. This paper aims to provide valuable insights for designing more flexible and adaptive next-generation embodied intelligent systems.
format Article
id doaj-art-a9f462b94aa6435dabb92a4dc19218d1
institution DOAJ
issn 2096-0271
language zho
publishDate 2025-03-01
publisher China InfoCom Media Group
record_format Article
series 大数据
spelling doaj-art-a9f462b94aa6435dabb92a4dc19218d12025-08-20T03:08:28ZzhoChina InfoCom Media Group大数据2096-02712025-03-0111739086967663Large language model-based embodied intelligence task planning: from single-agent to multi-agentJIA ZiqiWANG JianzongZHANG XulongQU XiaoyangWith the development of artificial intelligence, embodied intelligence and task planning have gradually become research hotspots. Traditional task planning methods lack flexibility when facing unpredictable environments, while large language models, with their powerful language understanding and multimodal capabilities, provide more comprehensive task planning solutions for intelligent agents, which offers new possibilities for addressing this issue. This paper reviews task planning methods based on large language models, covering different strategies in both single-agent and multi-agent contexts. Several representative frameworks and their performance and potential in practical applications are discussed. Specifically, this paper introduces single-agent large language model task planning methods, such as end-to-end planning, staged planning, and dynamic planning, and multi-agent large language model task planning methods, such as centralized planning, distributed planning, and hybrid planning. It also analyzes how these methods combine with reinforcement learning, multimodal perception, and other techniques to optimize the planning process. In addition, the paper discusses the characteristics, limitations, and challenges of large language model-based embodied intelligence task planning, and outlines the future development directions. This paper aims to provide valuable insights for designing more flexible and adaptive next-generation embodied intelligent systems.http://www.j-bigdataresearch.com.cn/thesisDetails#10.11959/j.issn.2096-0271.2025023task planninglarge language model
spellingShingle JIA Ziqi
WANG Jianzong
ZHANG Xulong
QU Xiaoyang
Large language model-based embodied intelligence task planning: from single-agent to multi-agent
大数据
task planning
large language model
title Large language model-based embodied intelligence task planning: from single-agent to multi-agent
title_full Large language model-based embodied intelligence task planning: from single-agent to multi-agent
title_fullStr Large language model-based embodied intelligence task planning: from single-agent to multi-agent
title_full_unstemmed Large language model-based embodied intelligence task planning: from single-agent to multi-agent
title_short Large language model-based embodied intelligence task planning: from single-agent to multi-agent
title_sort large language model based embodied intelligence task planning from single agent to multi agent
topic task planning
large language model
url http://www.j-bigdataresearch.com.cn/thesisDetails#10.11959/j.issn.2096-0271.2025023
work_keys_str_mv AT jiaziqi largelanguagemodelbasedembodiedintelligencetaskplanningfromsingleagenttomultiagent
AT wangjianzong largelanguagemodelbasedembodiedintelligencetaskplanningfromsingleagenttomultiagent
AT zhangxulong largelanguagemodelbasedembodiedintelligencetaskplanningfromsingleagenttomultiagent
AT quxiaoyang largelanguagemodelbasedembodiedintelligencetaskplanningfromsingleagenttomultiagent