TPTU：基於大型語言模型的人工智慧代理的任務規劃和工具使用

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

August 7, 2023

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

cs.AI

摘要

隨著自然語言處理的最新進展，大型語言模型（LLMs）已成為各種現實應用中強大的工具。儘管它們強大，LLMs 的固有生成能力可能無法應對需要任務規劃和外部工具使用結合的複雜任務。本文首先提出了一個針對基於LLMs的AI代理人量身定制的結構化框架，並討論應對複雜問題所需的關鍵能力。在這個框架內，我們設計了兩種不同類型的代理人（即一步代理人和順序代理人）來執行推理過程。隨後，我們使用各種LLMs實例化框架，並評估它們在典型任務上的任務規劃和工具使用（TPTU）能力。通過強調關鍵發現和挑戰，我們的目標是為研究人員和從業者提供一個有用的資源，以利用LLMs在其AI應用中的威力。我們的研究強調了這些模型的巨大潛力，同時也確定了需要更多調查和改進的領域。

English

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.