让大模型在千种工具中智能选材，不卡顿还省资源。
Dynamic ReAct: Scalable Tool Selection for Large-Scale MCP Environments
- 用搜索加载机制动态筛选工具，避免全量加载
- 实验显示工具加载量减少50%，任务完成率不变
- 适合需要大量工具的复杂自动化场景
我们提出 Dynamic ReAct，一种新方法，使 ReAct 类智能体能在包含数百甚至数千个可用工具的 Model Control Protocol (MCP) 环境中高效运行，突破大语言模型上下文记忆限制。针对工具数量庞大导致一次性加载不可行的问题，我们设计并评估了五种逐步优化的架构，最终实现一种搜索-加载机制，在极低计算开销下完成智能工具选择。实验表明，该方法可将工具加载量最多降低50%，同时保持任务完成准确率，推动通用型人工智能代理在多样化任务环境中实现动态适应。
原文摘要 · Abstract (English)
We present Dynamic ReAct, a novel approach for enabling ReAct agents to efficiently operate with extensive Model Control Protocol (MCP) tool sets that exceed the contextual memory limitations of large language models. Our approach addresses the fundamental challenge of tool selection in environments containing hundreds or thousands of available tools, where loading all tools simultaneously is computationally infeasible. We propose and evaluate five distinct architectures that progressively refine the tool selection process, culminating in a search-and-load mechanism that achieves intelligent tool selection with minimal computational overhead. Our experimental results demonstrate that the proposed approach reduces tool loading by up to 50% while maintaining task completion accuracy, advancing the path towards truly general-purpose AI agents capable of dynamically adapting to diverse task environments.
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。