arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2308.03427cs.AI

TPTU:基于大型语言模型的AI代理用于任务规划和工具使用

TPTU: Large Language Model-based AI Agents for Task Planning and Tool Usage

University of Chinese Academy of Sciences(中国科学院大学);SenseTime Research(商汤科技研究院);HKUST(香港科技大学)

Jingqing Ruan, Yihong Chen, Bin Zhang, Zhiwei Xu, Tianpeng Bao, Guoqing Du, Shiwei Shi, Hangyu Mao, Ziyue Li, Xingyu Zeng, Rui Zhao

AI总结:

本文提出基于大型语言模型的AI代理框架,设计两种代理类型以提升任务规划和工具使用能力,并通过实验验证其在复杂任务中的有效性。

摘要:

随着自然语言处理的最新进展,大型语言模型(LLMs)已逐渐成为各种现实世界应用中的强大工具。尽管它们能力出众,但LLMs固有的生成能力可能不足以处理需要结合任务规划和外部工具使用的复杂任务。在本文中,我们首先提出一个针对基于LLM的AI代理的结构化框架,并讨论解决复杂问题所需的关键能力。在此框架内,我们设计了两种不同的代理(即一步代理和顺序代理)来执行推理过程。随后,我们使用各种LLMs实例化该框架,并在典型任务上评估其任务规划和工具使用(TPTU)能力。通过突出关键发现和挑战,我们的目标是为研究人员和实践者提供一个有用的资源,以利用LLMs在AI应用中的强大能力。我们的研究强调了这些模型的巨大潜力,同时也指出了需要进一步研究和改进的领域。

英文摘要:

With recent advancements in natural language processing, Large Language Models (LLMs) have emerged as powerful tools for various real-world applications. Despite their prowess, the intrinsic generative abilities of LLMs may prove insufficient for handling complex tasks which necessitate a combination of task planning and the usage of external tools. In this paper, we first propose a structured framework tailored for LLM-based AI Agents and discuss the crucial capabilities necessary for tackling intricate problems. Within this framework, we design two distinct types of agents (i.e., one-step agent and sequential agent) to execute the inference process. Subsequently, we instantiate the framework using various LLMs and evaluate their Task Planning and Tool Usage (TPTU) abilities on typical tasks. By highlighting key findings and challenges, our goal is to provide a helpful resource for researchers and practitioners to leverage the power of LLMs in their AI applications. Our study emphasizes the substantial potential of these models, while also identifying areas that need more investigation and improvement.

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。

↑