让智能体在海量工具中精准导航，支持多智能体协作与抗干扰。
ACE-Router: Generalizing History-Aware Routing from MCP Tools to the Agent Web
- 基于依赖图生成多轮轨迹，训练能理解上下文的历史感知路由
- 在MCP-Universe和MCP-Mark上表现优于现有方法，可扩展至大规模工具集
- 适合构建开放生态中的通用调度系统，尤其适用于复杂任务场景
随着智能体网络和模型上下文协议（MCP）的发展，智能体生态系统正演变为开放协作网络，可用工具呈指数级增长。然而当前架构面临严重的可扩展性与泛化瓶颈。为此，我们提出ACE-Router，一种用于训练历史感知路由的流水线，以实现大规模生态中的精准导航。通过利用富含依赖关系的候选工具图合成多轮交互轨迹，我们有效训练出具备动态上下文理解能力的路由器，构建了即插即用的轻量级路由智能体。在真实世界基准MCP-Universe和MCP-Mark上的实验表明，ACE-Router表现出卓越性能。值得注意的是，该方法不仅在少量调整下即可泛化至多智能体协作，还对噪声具有极强鲁棒性，并能高效扩展至超大规模候选空间。这些发现为开放生态中的通用编排提供了坚实的实证基础。
原文摘要 · Abstract (English)
With the rise of the Agent Web and Model Context Protocol (MCP), the agent ecosystem is evolving into an open collaborative network, exponentially increasing accessible tools. However, current architectures face severe scalability and generality bottlenecks. To address this, we propose ACE-Router, a pipeline for training history-aware routers to empower precise navigation in large-scale ecosystems. By leveraging a dependency-rich candidate Graph to synthesize multi-turn trajectories, we effectively train routers with dynamic context understanding to create the plug-and-play Light Routing Agent. Experiments on the real-world benchmarks MCP-Universe and MCP-Mark demonstrate superior performance. Notably, ACE-Router exhibits critical properties for the future Agent Web: it not only generalizes to multi-agent collaboration with minimal adaptation but also maintains exceptional robustness against noise and scales effectively to massive candidate spaces. These findings provide a strong empirical foundation for universal orchestration in open-ended ecosystems.
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。