| 注册
首页|期刊导航|计算机工程|大模型工具学习:方法、作用与机制

大模型工具学习:方法、作用与机制

LIAO Niuyu TIAN Yun LI Yansong XUE Haifeng DU Changkun ZHANG Guohua

计算机工程2025,Vol.51Issue(12):1-17,17.
计算机工程2025,Vol.51Issue(12):1-17,17.DOI:10.19678/j.issn.1000-3428.0253230

大模型工具学习:方法、作用与机制

Tool Learning with Large Language Models:Methods,Functions,and Mechanisms

LIAO Niuyu 1TIAN Yun 2LI Yansong 1XUE Haifeng 3DU Changkun 4ZHANG Guohua4

作者信息

  • 1. School of Artificial Intelligence,Beijing Normal University,Beijing 100875,China
  • 2. School of Artificial Intelligence,Beijing Normal University,Beijing 100875,China||Engineering Research Center of Integration and Application of Digital Learning Technology,Ministry of Education,Beijing 100068,China
  • 3. Engineering Research Center of Integration and Application of Digital Learning Technology,Ministry of Education,Beijing 100068,China
  • 4. Aerospace Science and Industry Group Intelligent Technology Research Institute Co.,Ltd.,Beijing 100043,China
  • 折叠

摘要

Abstract

In recent years,Large Language Models(LLMs)such as GPT,LLaMA,Qwen,and DeepSeek,have achieved significant breakthroughs in natural language processing,computer vision,multimodal learning,and other fields.However,constrained by factors such as their reasoning mechanisms,parameter scales,and the inherent knowledge contained within their training data,these models often suffer from issues like"hallucinations"-characterized by inaccurate answers and even factual deviations-when handling complex tasks,addressing questions from professional domains,or generating time-sensitive content.These limitations severely hinder their application in high-reliability scenarios.The"tool learning"paradigm is attracting increasing attention as a promising solution to these capability bottlenecks.Its primary objective is to enable LLMs to understand and utilize external tools to complete specific tasks.By invoking external tools,such as databases,search engines,and mathematical tools,LLMs can transcend their parameterized knowledge;enhance their reasoning,decision-making,and execution capabilities;and mitigate hallucination problems.This paper systematically reviews the development context and technical advancements in LLM tool learning,analyzes the expansion of LLM capabilities through tools,summarizes tool invocation mechanisms ranging from in-context learning to fine-tuning training,and discusses key issues including performance optimization and adaptive tool generation.The paper also analyzes evaluation methods for LLM tool invocation,summarizes the current challenges in tool learning,and outlines future research directions.

关键词

大模型/工具学习/使用范式/工具调用机制/工具学习优化

Key words

Large Language Model(LLM)/tool learning/usage paradigm/tool invocation mechanism/tool learning optimization

分类

信息技术与安全科学

引用本文复制引用

LIAO Niuyu,TIAN Yun,LI Yansong,XUE Haifeng,DU Changkun,ZHANG Guohua..大模型工具学习:方法、作用与机制[J].计算机工程,2025,51(12):1-17,17.

基金项目

国家自然科学基金面上项目(62172047) (62172047)

数字化学习技术集成与应用教育部工程研究中心创新基金(1311006) (1311006)

中央高校基本科研业务费专项资金(2243200003). (2243200003)

计算机工程

OA北大核心

1000-3428

访问量0
|
下载量0
段落导航相关论文