Saved in:
Bibliographic Details
Main Authors: Yao, Zhiyuan, Xu, Zishan, Guo, Yifu, Han, Zhiguang, Yang, Cheng, Zhang, Shuo, Zhang, Weinan, Zeng, Xingshan, Liu, Weiwen
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.08276
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917419489951744
author Yao, Zhiyuan
Xu, Zishan
Guo, Yifu
Han, Zhiguang
Yang, Cheng
Zhang, Shuo
Zhang, Weinan
Zeng, Xingshan
Liu, Weiwen
author_facet Yao, Zhiyuan
Xu, Zishan
Guo, Yifu
Han, Zhiguang
Yang, Cheng
Zhang, Shuo
Zhang, Weinan
Zeng, Xingshan
Liu, Weiwen
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_08276
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ACE-Router: Generalizing History-Aware Routing from MCP Tools to the Agent Web
Yao, Zhiyuan
Xu, Zishan
Guo, Yifu
Han, Zhiguang
Yang, Cheng
Zhang, Shuo
Zhang, Weinan
Zeng, Xingshan
Liu, Weiwen
Artificial Intelligence
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.
title ACE-Router: Generalizing History-Aware Routing from MCP Tools to the Agent Web
topic Artificial Intelligence
url https://arxiv.org/abs/2601.08276