MetaToolAgent：通过元学习实现LLM中通用工具使用的迈进
MetaToolAgent: Towards Generalizable Tool Usage in LLMs through Meta-Learning
AI总结：
MetaToolAgent通过元学习方法提升LLM在多样工具中的泛化能力，解决现有工具选择方法在实际部署中泛化能力不足的问题。
摘要：
工具学习对于大型语言模型（LLMs）日益重要，以便有效协调和利用多样化的工具集以解决复杂的现实任务。通过选择和整合适当的工具，LLMs的能力超越了纯粹的语言理解，能够执行专门的功能。然而，现有工具选择方法往往局限于有限的工具集，并且在实际部署中遇到新工具时难以泛化。为了解决这些挑战，我们引入了一个涵盖7个领域的综合数据集，包含155种工具和9,377个问题-答案对，模拟了现实的整合场景。此外，我们提出了MetaToolAgent（MTA），一种元学习方法，旨在提高跨工具的泛化能力。实验结果表明，MTA在未见过的工具上显著优于基线方法，证明了其在构建灵活且可扩展的系统中的潜力，这些系统需要动态的工具协调。
英文摘要：
Tool learning is increasingly important for large language models (LLMs) to effectively coordinate and utilize a diverse set of tools in order to solve complex real-world tasks. By selecting and integrating appropriate tools, LLMs extend their capabilities beyond pure language understanding to perform specialized functions. However, existing methods for tool selection often focus on limited tool sets and struggle to generalize to novel tools encountered in practical deployments. To address these challenges, we introduce a comprehensive dataset spanning 7 domains, containing 155 tools and 9,377 question-answer pairs, which simulates realistic integration scenarios. Additionally, we propose MetaToolAgent (MTA), a meta-learning approach designed to improve cross-tool generalization. Experimental results show that MTA significantly outperforms baseline methods on unseen tools, demonstrating its promise for building flexible and scalable systems that require dynamic tool coordination.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
