An Expert is Worth One Token: Synergizing Multiple Expert LLMs as Generalist via Expert Token Routing
Not on the map. Why?
Abstract (arXiv)
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-and-play 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.
Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 20 of its 25 references that are in the map. First posted on arXiv 25 Mar 2024.
Builds on
20 of 25 references.
References · 20
- 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
- 2020Measuring Massive Multitask Language Understandingcited by 7,963
- 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
- 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
- 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
- 2023Code Llama: Open Foundation Models for Codecited by 2,139
- 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
- 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
- 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,181
- 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 688
- 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 564
- 2023A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaborationcited by 290
8 more
- 2023Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaborationcited by 251
- 2023ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddingscited by 240
- 2023ExpertPrompting: Instructing Large Language Models to be Distinguished Expertscited by 142
- 2024Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffoldingcited by 117
- 2024LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wildcited by 68
- 2023DISC-FinLLM: A Chinese Financial Large Language Model based on Multiple Experts Fine-tuningcited by 64
- 2023π-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolationcited by 40
- 2023Unnatural language processing: How do language models handle machine-generated prompts?cited by 8
Built on by
Citing papers per year: 2024: 3; 2025: 2; 2026: 3.
8 papers.
- 2024Programming Refusal with Conditional Activation Steeringcited by 206
- 2024Towards Modular LLMs by Building and Reusing a Library of LoRAscited by 72
- 2024AgentStore: Scalable Integration of Heterogeneous Agents As Specialized Generalist Computer Assistantcited by 27
- 2025Doing More with Less: A Survey on Routing Strategies for Resource Optimisation in Large Language Model-Based Systemscited by 20
- 2025Large-Small Model Collaboration for Enhancing Edge-Deployed Small Modelscited by 2
- 2026Divergence Decoding: Training-Free Capability Fusioncited by 0
- 2026Beyond Solo and Consistency: Vindicating Multi-Agent Debate via Conditional Progressive Pruningcited by 0
- 2026Training Language Models To Be Coherent Decision-Makerscited by 0
- 2026Training Language Models To Be Coherent Decision-Makers6 Oct 2026
- 2026Beyond Solo and Consistency: Vindicating Multi-Agent Debate via Conditional Progressive Pruning27 Sep 2026
- 2026Divergence Decoding: Training-Free Capability Fusion28 Jul 2026
- 2025Large-Small Model Collaboration for Enhancing Edge-Deployed Small Models13 Mar 2025
- 2025Doing More with Less: A Survey on Routing Strategies for Resource Optimisation in Large Language Model-Based Systems1 Feb 2025
- 2024AgentStore: Scalable Integration of Heterogeneous Agents As Specialized Generalist Computer Assistant24 Oct 2024
- 2024Programming Refusal with Conditional Activation Steering6 Sep 2024
- 2024Towards Modular LLMs by Building and Reusing a Library of LoRAs18 May 2024