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
摘要
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
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper1
问问它们各自怎么用它它引用的顶会 Paper7
- BERTScore: Evaluating Text Generation with BERTTianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger 等ICLR 2020 · 被引用 8,443 次
- Measuring Massive Multitask Language UnderstandingDan Hendrycks, Collin Burns, Steven Basart, Andy Zou 等ICLR 2021 · 被引用 7,905 次
- Improving Factuality and Reasoning in Language Models through Multiagent DebateYilun Du, Shuang Li, Antonio Torralba, Joshua B. Tenenbaum 等ICML 2024 · 被引用 1,562 次
- ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool EmbeddingsShibo Hao, Tianyang Liu, Zhen Wang, Zhiting HuNeurIPS 2023 · 被引用 315 次
- LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative FusionDongfu Jiang, Xiang Ren, Bill Yuchen LinACL 2023 · 被引用 95 次
相关 Paper
- Token-Level LLM Collaboration via FusionRouteNuoya Xiong, Yuhang Zhou, Hanqing Zeng, Zhaorun Chen 等ICML 2026 · 被引用 7 次
- Glider: Global and Local Instruction-Driven Expert RouterPingzhi Li, Prateek Yadav, Jaehong Yoon, Jie Peng 等EMNLP 2025 · 被引用 1 次
- Self-MoE: Towards Compositional Large Language Models with Self-Specialized ExpertsJunmo Kang, Leonid Karlinsky, Hongyin Luo, Zhen Wang 等ICLR 2025
- Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement LearningHaozhen Zhang, Tao Feng, Jiaxuan YouNeurIPS 2025 · 被引用 81 次
- DiSRouter: Distributed Self-Routing for LLM SelectionsHang Zheng, Hongshen Xu, Yongkai.lin, Shuai Fan 等ICLR 2026 · 被引用 6 次
