Haoming Li, Zhaoliang Chen, Jonathan Zhang, Fei Liu
{"title":"LASP:大型语言模型辅助人工智能规划技术现状调查","authors":"Haoming Li, Zhaoliang Chen, Jonathan Zhang, Fei Liu","doi":"arxiv-2409.01806","DOIUrl":null,"url":null,"abstract":"Effective planning is essential for the success of any task, from organizing\na vacation to routing autonomous vehicles and developing corporate strategies.\nIt involves setting goals, formulating plans, and allocating resources to\nachieve them. LLMs are particularly well-suited for automated planning due to\ntheir strong capabilities in commonsense reasoning. They can deduce a sequence\nof actions needed to achieve a goal from a given state and identify an\neffective course of action. However, it is frequently observed that plans\ngenerated through direct prompting often fail upon execution. Our survey aims\nto highlight the existing challenges in planning with language models, focusing\non key areas such as embodied environments, optimal scheduling, competitive and\ncooperative games, task decomposition, reasoning, and planning. Through this\nstudy, we explore how LLMs transform AI planning and provide unique insights\ninto the future of LM-assisted planning.","PeriodicalId":501479,"journal":{"name":"arXiv - CS - Artificial Intelligence","volume":"81 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"LASP: Surveying the State-of-the-Art in Large Language Model-Assisted AI Planning\",\"authors\":\"Haoming Li, Zhaoliang Chen, Jonathan Zhang, Fei Liu\",\"doi\":\"arxiv-2409.01806\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Effective planning is essential for the success of any task, from organizing\\na vacation to routing autonomous vehicles and developing corporate strategies.\\nIt involves setting goals, formulating plans, and allocating resources to\\nachieve them. LLMs are particularly well-suited for automated planning due to\\ntheir strong capabilities in commonsense reasoning. They can deduce a sequence\\nof actions needed to achieve a goal from a given state and identify an\\neffective course of action. However, it is frequently observed that plans\\ngenerated through direct prompting often fail upon execution. Our survey aims\\nto highlight the existing challenges in planning with language models, focusing\\non key areas such as embodied environments, optimal scheduling, competitive and\\ncooperative games, task decomposition, reasoning, and planning. Through this\\nstudy, we explore how LLMs transform AI planning and provide unique insights\\ninto the future of LM-assisted planning.\",\"PeriodicalId\":501479,\"journal\":{\"name\":\"arXiv - CS - Artificial Intelligence\",\"volume\":\"81 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Artificial Intelligence\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.01806\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Artificial Intelligence","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.01806","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
LASP: Surveying the State-of-the-Art in Large Language Model-Assisted AI Planning
Effective planning is essential for the success of any task, from organizing
a vacation to routing autonomous vehicles and developing corporate strategies.
It involves setting goals, formulating plans, and allocating resources to
achieve them. LLMs are particularly well-suited for automated planning due to
their strong capabilities in commonsense reasoning. They can deduce a sequence
of actions needed to achieve a goal from a given state and identify an
effective course of action. However, it is frequently observed that plans
generated through direct prompting often fail upon execution. Our survey aims
to highlight the existing challenges in planning with language models, focusing
on key areas such as embodied environments, optimal scheduling, competitive and
cooperative games, task decomposition, reasoning, and planning. Through this
study, we explore how LLMs transform AI planning and provide unique insights
into the future of LM-assisted planning.