--- title: "ACE-Router — paper by Yao et al. (2026) — summary and ideas" description: "As the Model Context Protocol (MCP) and the emerging Agent Web expose ever-larger… 53.44% accuracy on MCP-Universe. 2 references." authors: ["Zhiyuan Yao", "Zishan Xu", "Yifu Guo", "Zhiguang Han", "Cheng Yang", "Shuo Zhang", "Weinan Zhang", "Xingshan Zeng", "Weiwen Liu"] year: 2026 venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)" source: "https://aclanthology.org/2026.acl-long.281/" doi: "10.18653/v1/2026.acl-long.281" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/yao-2026-ace-router-generalizing-history-aware/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yao-2026-ace-router-generalizing-history-aware/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/21/) / ACE-Router: Generalizing History-Aware Routing from MCP Tools to the Agent Web # ACE-Router: Generalizing History-Aware Routing from MCP Tools to the Agent Web **Authors:** [Zhiyuan Yao](https://md.research.elamur.ai/free/en/authors/zhiyuan-yao/), [Zishan Xu](https://md.research.elamur.ai/free/en/authors/zishan-xu/), [Yifu Guo](https://md.research.elamur.ai/free/en/authors/yifu-guo/), Zhiguang Han, [Cheng Yang](https://md.research.elamur.ai/free/en/authors/cheng-hong-yang/), [Shuo Zhang](https://md.research.elamur.ai/free/en/authors/shuo-zhang/), [Weinan Zhang](https://md.research.elamur.ai/free/en/authors/weinan-zhang/), [Xingshan Zeng](https://md.research.elamur.ai/free/en/authors/xingshan-zeng/) and [Weiwen Liu](https://md.research.elamur.ai/free/en/authors/weiwen-liu/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.281/) · [PDF](https://aclanthology.org/2026.acl-long.281.pdf) · [DOI 10.18653/v1/2026.acl-long.281](https://doi.org/10.18653/v1/2026.acl-long.281) · [OpenAlex](https://openalex.org/W7166873120) **Citations:** 0 citations (OpenAlex, 2026-10-14) ## Summary As the Model Context Protocol (MCP) and the emerging Agent Web expose ever-larger pools of tools and agents, picking the right one becomes a bottleneck. Listing every schema in the prompt runs out of context window. Embedding-based retrieval cannot separate near-duplicate tools and ignores what happened earlier in the conversation. ACE-Router addresses this with a pipeline for training routers that condition on both the query and the dialogue history. It works in three stages: - **Graph-based expansion.** A candidate graph links tools by similarity or dependency, and self-evolutionary mutation adds functionally close variants. - **Trajectory synthesis.** Random walks over this graph choose tool subsets. A multi-agent simulation then turns these subsets into multi-turn trajectories that serve as routing supervision. - **Deployment.** The trained router is packaged as the plug-and-play Light Routing Agent. On MCP-Universe and MCP-Mark, ACE-Router beats embedding retrievers, ReAct agents and strong LLM-based routers. It stays stable as noisy or real external tools are added, and it transfers to agent selection without extra fine-tuning. This makes it a practical basis for large-scale orchestration. ## Key points - ACE-Router reaches 53.44% accuracy on MCP-Universe and 60.00% on MCP-Mark in the clean setting. The best LLM router baseline on MCP-Universe is Gemini-2.5-Pro at 49.79%. - Under the Multi, +Mutation and +LiveMCP settings, ACE-Router's MCP-Universe accuracy stays roughly between 52.6% and 53%. Embedding retrievers fall to 20–32% once LiveMCP tools are added. - Training without dialogue history lowers accuracy from 53% to 48% on MCP-Universe and from 60% to 52% on MCP-Mark. The authors attribute this to lost sequential-dependency reasoning and lost error recovery. - Mutation enlarges the tool pool from 627 to 2,005 candidates. Removing mutation gives 47.12% / 44.00%, and vanilla fine-tuning gives 46.70% / 42.00% (MCP-Universe / MCP-Mark). - The Light Routing Agent uses only two interface tools, Router Invocation and Execution. Code is available at github.com/euyis1019/ACE-Router. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* ## Institutions - [Shanghai Jiao Tong University](https://md.research.elamur.ai/free/en/universities/shanghai-jiao-tong-university/) — University, Shanghai, China · 212 works · 19,544 citations - [Nanyang Technological University](https://md.research.elamur.ai/free/en/universities/nanyang-technological-university/) — University, Singapore, Singapore · 184 works · 27,484 citations - [Zhejiang University](https://md.research.elamur.ai/free/en/universities/zhejiang-university/) — University, Hangzhou, China · 224 works · 13,587 citations - [Huawei Technologies](https://md.research.elamur.ai/free/en/companies/huawei-technologies/) — Company, Shenzhen, China · 96 works · 15,432 citations - [Sun Yat-sen University](https://md.research.elamur.ai/free/en/universities/sun-yat-sen-university/) — University, Guangzhou, China · 72 works · 9,502 citations - [Hangzhou Dianzi University](https://md.research.elamur.ai/free/en/universities/hangzhou-dianzi-university/) — University, Hangzhou, China · 15 works · 1,061 citations 📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,730 works ## Cite Cite as: Zhiyuan Yao, Zishan Xu, Yifu Guo, Zhiguang Han, Cheng Yang, Shuo Zhang, Weinan Zhang, Xingshan Zeng and Weiwen Liu. 2026. ACE-Router: Generalizing History-Aware Routing from MCP Tools to the Agent Web. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{yao2026ace, title = {{ACE-Router: Generalizing History-Aware Routing from MCP Tools to the Agent Web}}, author = {Zhiyuan Yao, Zishan Xu, Yifu Guo, Zhiguang Han, Cheng Yang, Shuo Zhang, Weinan Zhang, Xingshan Zeng and Weiwen Liu}, booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, year = {2026}, doi = {10.18653/v1/2026.acl-long.281}, url = {https://doi.org/10.18653/v1/2026.acl-long.281} } ``` - [← previous AccurateRAG: A Framework for Building Accurate Retrieval-Augmented Question-Answering Applications](https://md.research.elamur.ai/free/en/papers/nguyen-2026-accuraterag-framework-building-accurate-retrieval/) - [next → Acehnese interference in students' spoken Arabic: A multi-level cross-linguistic analysis in an Indonesian Islamic boarding school](https://md.research.elamur.ai/free/en/papers/ahmad-2026-acehnese-interference-students-spoken-arabic/) - [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/21/) ## References 2 references, 1 of them with a card of ours. ↗ leads to the work. 1. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, and 1 others. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv preprint arXiv:2303.08774. 2. Anthropic. 2024. Introducing the Model Context Protocol. [https://www.anthropic.com/news/](https://www.anthropic.com/news/) model-context-protocol. \#\# Conclusion [↗](https://www.anthropic.com/news/) *Updated 2 November 2026*