Humans possess an extraordinary ability to create and utilize tools. With the advent of foundation models, artificial intelligence systems have the potential to be equally adept in tool use as humans. This paradigm, which is dubbed as tool learning with foundation models , combines the strengths of tools and foundation models to achieve enhanced accuracy, efficiency, and automation in problem-solving. This paper presents a systematic investigation and comprehensive review of tool learning. We first introduce the background of tool learning, including its cognitive origins, the paradigm shift of foundation models, and the complementary roles of tools and models. Then we recapitulate existing tool learning research and formulate a general framework: starting from understanding the user instruction, models should learn to decompose a complex task into several subtasks, dynamically adjust their plan through reasoning, and effectively conquer each sub-task by selecting appropriate tools. We also discuss how to train models for improved tool-use capabilities and facilitate generalization in tool learning. Finally, we discuss several open problems that require further investigation, such as ensuring trustworthy tool use, enabling tool creation with foundation models, and addressing personalization challenges. Overall, we hope this paper could inspire future research in integrating tools with foundation models.

中文翻译：

---

使用基础模型进行工具学习


人类拥有创造和使用工具的非凡能力。随着基础模型的出现，人工智能系统有可能在工具使用方面与人类一样熟练。这种范式被称为 使用基础模型进行工具学习 ，结合了工具和基础模型的优势，以提高解决问题的准确性、效率和自动化。本文对工具学习进行了系统调查和全面回顾。我们首先介绍了工具学习的背景，包括它的认知起源、基础模型的范式转变以及工具和模型的互补作用。然后，我们总结现有的工具学习研究，并制定一个通用框架：从理解用户指令开始，模型应该学会将一个复杂的任务分解成几个子任务，通过推理动态调整自己的计划，并通过选择合适的工具有效地征服每个子任务。我们还讨论了如何训练模型以提高工具使用能力并促进工具学习的泛化。最后，我们讨论了几个需要进一步调查的未决问题，例如确保可信的工具使用、支持使用基础模型创建工具以及解决个性化挑战。总的来说，我们希望这篇论文可以启发未来将工具与基础模型集成的研究。