An Expert is Worth One Token: Synergizing Multiple Expert LLMs as Generalist via Expert Token Routing
Ziwei Chai, Guoyin Wang, Jing Su, Tianjie Zhang, Xuanwen Huang, Xuwu Wang, Jingjing Xu, Jianbo Yuan, Hongxia Yang, Fei Wu, Yang Yang
Abstract
We present Expert-Token-Routing, a unified generalist framework that facilitates seamless integration of multiple expert LLMs. Our framework represents expert LLMs as special expert tokens within the vocabulary of a meta LLM. The meta LLM can route to an expert LLM like generating new tokens. Expert-Token-Routing not only supports learning the implicit expertise of expert LLMs from existing instruction dataset but also allows for dynamic extension of new expert LLMs in a plug-andplay manner. It also conceals the detailed collaboration process from the user's perspective, facilitating interaction as though it were a singular LLM. Our framework outperforms various existing multi-LLM collaboration paradigms across benchmarks that incorporate six diverse expert domains, demonstrating effectiveness and robustness in building generalist LLM system via synergizing multiple expert LLMs. 1
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers1
Ask how each one uses itBuilds on7
- BERTScore: Evaluating Text Generation with BERTTianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger et al.ICLR 2020 · 8,443 citations
- Measuring Massive Multitask Language UnderstandingDan Hendrycks, Collin Burns, Steven Basart, Andy Zou et al.ICLR 2021 · 7,905 citations
- Improving Factuality and Reasoning in Language Models through Multiagent DebateYilun Du, Shuang Li, Antonio Torralba, Joshua B. Tenenbaum et al.ICML 2024 · 1,562 citations
- ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool EmbeddingsShibo Hao, Tianyang Liu, Zhen Wang, Zhiting HuNeurIPS 2023 · 315 citations
- LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative FusionDongfu Jiang, Xiang Ren, Bill Yuchen LinACL 2023 · 95 citations
Related papers
- Token-Level LLM Collaboration via FusionRouteNuoya Xiong, Yuhang Zhou, Hanqing Zeng, Zhaorun Chen et al.ICML 2026 · 7 citations
- Glider: Global and Local Instruction-Driven Expert RouterPingzhi Li, Prateek Yadav, Jaehong Yoon, Jie Peng et al.EMNLP 2025 · 1 citation
- Self-MoE: Towards Compositional Large Language Models with Self-Specialized ExpertsJunmo Kang, Leonid Karlinsky, Hongyin Luo, Zhen Wang et al.ICLR 2025
- Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement LearningHaozhen Zhang, Tao Feng, Jiaxuan YouNeurIPS 2025 · 81 citations
- DiSRouter: Distributed Self-Routing for LLM SelectionsHang Zheng, Hongshen Xu, Yongkai.lin, Shuai Fan et al.ICLR 2026 · 6 citations
