梳理大模型工具使用三大范式，揭示其演进路径与挑战
Agentic Tool Use in Large Language Models
- 按提示即用、监督学习、奖励驱动三类归纳工具使用方法
- 系统分析各类方法在真实场景中的表现差异与失效原因
- 适合研究大模型自主性与工具集成的开发者与学者参考
大型语言模型正越来越多地被部署为自主代理，但其在现实世界中的有效性依赖于可靠的信息检索、计算和外部操作工具。现有研究在任务、工具类型和训练设置上分散，缺乏对工具使用方法差异与演化的统一视角。本文将文献归纳为三种范式：提示即用、监督工具学习和奖励驱动的工具策略学习，分析其方法、优势与失败模式，回顾评估体系，指出关键挑战，旨在解决碎片化问题，提供更结构化的代理工具使用演进图景。
原文摘要 · Abstract (English)
Large language models are increasingly being deployed as autonomous agents yet their real world effectiveness depends on reliable tools for information retrieval, computation and external action. Existing studies remain fragmented across tasks, tool types, and training settings, lacking a unified view of how tool-use methods differ and evolve. This paper organizes the literature into three paradigms: prompting as plug-and-play, supervised tool learning and reward-driven tool policy learning, analyzes their methods, strengths and failure modes, reviews the evaluation landscape and highlights key challenges, aiming to address this fragmentation and provide a more structured evolutionary view of agentic tool use.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。