TPTU：基于大型语言模型的人工智能代理的任务规划和工具使用

摘要

随着自然语言处理的最新进展，大型语言模型（LLMs）已经成为各种现实世界应用的强大工具。尽管它们非常强大，但LLMs的固有生成能力可能不足以处理需要任务规划和外部工具使用相结合的复杂任务。在本文中，我们首先提出了一个专为基于LLMs的人工智能代理量身定制的结构化框架，并讨论了解决复杂问题所必需的关键能力。在这个框架内，我们设计了两种不同类型的代理（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实例化了这个框架，并评估它们在典型任务上的任务规划和工具使用（TPTU）能力。通过突出主要发现和挑战，我们的目标是为研究人员和从业者提供一个有用的资源，以利用LLMs在其人工智能应用中的力量。我们的研究强调了这些模型的巨大潜力，同时也确定了需要更多调查和改进的领域。

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.

TPTU：基于大型语言模型的人工智能代理的任务规划和工具使用

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

摘要

Support