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.
翻译:随着自然语言处理领域的最新进展,大语言模型已成为各种现实应用中的强大工具。尽管其能力卓越,但大语言模型固有的生成能力在处理需要结合任务规划与外部工具使用的复杂任务时可能显得不足。本文首先提出一个专为基于大语言模型的人工智能代理设计的结构化框架,并讨论了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类型的代理(即单步代理与序列代理)来执行推理过程。随后,我们使用多种大语言模型实例化该框架,并在典型任务上评估其任务规划与工具使用能力。通过总结关键发现与挑战,我们的目标是为研究者和实践者提供有益参考,以在其人工智能应用中充分发挥大语言模型的潜力。本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探索和改进的领域。