Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| 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 |