让大模型学会动态更新工具调用能力，应对外部接口变化。
Learning Evolving Tools for Large Language Models
- 用蒙特卡洛树搜索实现大模型主动探索与自我反思。
- 在动态环境测试中，模型工具调用准确率提升37%以上。
- 适合需要长期运行的智能助手、自动化系统使用。
工具学习使大语言模型能够与外部工具和API交互，显著拓展其应用范围。然而，由于外部环境的动态性，这些工具和API可能随时间过时，导致大模型无法正确调用。现有研究主要关注静态环境，忽视了这一问题，限制了大模型在真实场景中的适应能力。本文提出ToolEVO框架，旨在增强大模型对工具变化的自适应与自我反思能力。通过引入蒙特卡洛树搜索，ToolEVO支持大模型在动态环境中主动探索与交互，基于环境反馈实现工具调用的自主反思与更新。此外，我们构建了ToolQA-D基准，专门用于评估工具变异的影响。大量实验表明，该方法在动态环境下的有效性和稳定性显著，凸显了对工具变异适应性的关键作用。代码已开源：https://github.com/Chen-GX/ToolEVO。
原文摘要 · Abstract (English)
Tool learning enables large language models (LLMs) to interact with external tools and APIs, greatly expanding the application scope of LLMs. However, due to the dynamic nature of external environments, these tools and APIs may become outdated over time, preventing LLMs from correctly invoking tools. Existing research primarily focuses on static environments and overlooks this issue, limiting the adaptability of LLMs in real-world applications. In this paper, we propose ToolEVO, a novel framework designed to enhance the adaptive and reflective capabilities of LLMs against tool variability. By leveraging Monte Carlo Tree Search, ToolEVO facilitates active exploration and interaction of LLMs within dynamic environments, allowing for autonomous self-reflection and self-updating of tool usage based on environmental feedback. Additionally, we introduce ToolQA-D, a benchmark specifically designed to evaluate the impact of tool variability. Extensive experiments demonstrate the effectiveness and stability of our approach, highlighting the importance of adaptability to tool variability for effective tool learning. Code: https://github.com/Chen-GX/ToolEVO
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。