LLM-Based Agents for Tool Learning: A Survey
Authors:
Top Cited Papers
Open Access
- 26 June 2025
- journal article
- research article
- Published by Springer Nature in Data Science and Engineering
- Vol. 10 (4) , 533-563
Abstract
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.Keywords
Funding Information
- Natural Science Foundation of China (62406061)
- National Natural Science Foundation of China (62432002)
- Natural Science Foundation of Shandong Province (ZR2023QF159)
This publication has 104 references indexed in Scilit:
- TDAG: A multi-agent framework based on dynamic Task Decomposition and Agent GenerationNeural Networks, 2025
- ControlLLM: Augment Language Models with Tools by Searching on Graphs2024
- LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents2024
- TPE: Towards Better Compositional Reasoning over Cognitive Tools via Multi-persona Collaboration2024
- Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs2024
- Simulating Individual Infection Risk over Big Trajectory Data2024
- MechAgents: Large language model multi-agent collaborations can solve mechanics problems, generate new data, and integrate knowledgeExtreme Mechanics Letters, 2024
- BioTreasury: a community-based repository enabling indexing and rating of bioinformatics toolsScience China Life Sciences, 2023
- The imperative for regulatory oversight of large language models (or generative AI) in healthcarenpj Digital Medicine, 2023
- An Introduction to First-Order Logic1977