ACE-Router: Generalizing History-Aware Routing from MCP Tools to the Agent Web

TL;DR

ACE-Router introduces a history-aware routing pipeline that enhances navigation, scalability, and robustness in large-scale Agent Web ecosystems, enabling effective multi-agent collaboration.

Contribution

It presents a novel training pipeline for history-aware routers that generalize across multi-agent systems with minimal adaptation.

Findings

ACE-Router outperforms existing methods on MCP-Universe and MCP-Mark benchmarks.

It generalizes well to multi-agent collaboration with minimal adaptation.

It maintains robustness against noise and scales to large candidate spaces.

Abstract

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.