Recently, tool learning with large language models (LLMs) has emerged as a
promising paradigm for augmenting the capabilities of LLMs to tackle highly
complex problems. Despite growing attention and rapid advancements in this
field, the existing literature remains fragmented and lacks systematic
organization, posing barriers to entry for newcomers. This gap motivates us to
conduct a comprehensive survey of existing works on tool learning with LLMs. In
this survey, we focus on reviewing existing literature from the two primary
aspects (1) why tool learning is beneficial and (2) how tool learning is
implemented, enabling a comprehensive understanding of tool learning with LLMs.
We first explore the "why" by reviewing both the benefits of tool integration
and the inherent benefits of the tool learning paradigm from six specific
aspects. In terms of "how", we systematically review the literature according
to a taxonomy of four key stages in the tool learning workflow: task planning,
tool selection, tool calling, and response generation. Additionally, we provide
a detailed summary of existing benchmarks and evaluation methods, categorizing
them according to their relevance to different stages. Finally, we discuss
current challenges and outline potential future directions, aiming to inspire
both researchers and industrial developers to further explore this emerging and
promising area.

最近，利用大型语言模型（LLMs）进行工具学习已经成为增强 LLMs 能力以解决高度复杂问题的一种有前景的范式。尽管这一领域受到越来越多关注和快速发展，但现有文献仍然零散且缺乏系统组织，对于新手来说存在进入障碍。本文通过对现有关于 LLMs 工具学习的文献进行综述，旨在探讨为什么工具学习有益以及如何实现工具学习，从而全面了解 LLMs 工具学习。首先，我们通过从六个具体方面回顾工具整合的益处以及工具学习范式的内在益处来探讨 “为什么”。在 “如何” 方面，我们根据工具学习工作流程的四个关键阶段（任务规划、工具选择、工具调用和响应生成）系统综述了现有文献。此外，我们还详细总结了现有的基准和评估方法，并根据其与不同阶段的相关性进行分类。最后，我们讨论了当前的挑战，并概述了潜在的未来方向，旨在鼓励研究人员和工业开发者进一步探索这一新兴而有前景的领域。