LLM-Based Agents for Tool Learning: A Survey
Data Science and Engineering · 2025-12 · 10 (4) · 533-563
DOI: 10.1007/s41019-025-00296-9 ↗Kurz gefasst
Fachartikel in der Zeitschrift Data Science and Engineering, online erschienen am 26.06.2025. Verfasst von Weikai Xu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 73-mal zitiert (Crossref) und nennt 171 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of China, National Natural Science Foundation of China, Natural Science Foundation of Shandong Province.
Abstract (Originalsprache)
Human beings capable of making and using tools can accomplish tasks far beyond their innate abilities, and this paradigm of integration with tools may not be limited to humans themselves. Recently, the large language model (LLM) has demonstrated immense potential across various fields with its unique planning and reasoning abilities. However, there are still many challenges beyond its capabilities due to deficiencies in its training data and inherent illusions. Thus, integrating LLMs and tools into tool learning agents has become a new emerging research direction. To this end, we present a systematic investigation and comprehensive review of tool-learning agents in this paper. We start by introducing the definition of the tool learning task for Agents and then illustrating the typical architecture of the tool-learning models. Since these tools are all defined by users, LLM does not know what tools there are and what their functions are. Thus, LLMs should first find appropriate tools and split the tool retrieval methods into two categories: training-based and non-training-based. To accurately complete the user task, it is important to decompose the task into several sub-tasks and execute them in the correct order. Following that, we introduce the tool planning methods and organize these works by whether they rely on the model’s inherent reasoning capabilities for planning or utilize external reasoning tools. Due to the rapid development of this field, we also introduce an emerging frontier direction: using multimodal tools for LLM. In addition, we compile current open-source benchmarks and evaluation metrics, focusing on their scale, composition, calculation methods, and assessment dimensions. Next, we introduce several application scenarios for the LLM-based tool learning methods. Finally, we discuss the safety and ethical issues involved in tool learning.
Förderung
- Natural Science Foundation of China
- National Natural Science Foundation of China
- Natural Science Foundation of Shandong Province
Zitieren
APA
Xu, W., Huang, C., Gao, S., & Shang, S. (2025). LLM-Based Agents for Tool Learning: A Survey. Data Science and Engineering, 10(4), 533-563. https://doi.org/10.1007/s41019-025-00296-9
Vancouver
Xu W, Huang C, Gao S, Shang S. LLM-Based Agents for Tool Learning: A Survey. Data Science and Engineering. 2025;10(4):533-563. doi:10.1007/s41019-025-00296-9
BibTeX
@article{Xu2025,
author = {Xu, Weikai and Huang, Chengrui and Gao, Shen and Shang, Shuo},
title = {LLM-Based Agents for Tool Learning: A Survey},
journal = {Data Science and Engineering},
year = {2025},
volume = {10},
number = {4},
pages = {533--563},
doi = {10.1007/s41019-025-00296-9}
}
EUVIMED