mlsanityData to 14 Oct 2026

TagRouter: Learning Route to LLMs through Tags for Open-Domain Text Generation Tasks

arXiv 2506.12473 ↗First posted 14 Jun 2025cs.CLcited by 9

Not on the map. Why?

Abstract (arXiv)

Model routing allocates queries to the suitable model, improving system performance while reducing costs. However, existing routing methods face practical limitations that hinder scalability in large-scale applications and struggle to keep up with the rapid growth of the large language model (LLM) ecosystem. To tackle these challenges, we propose TagRouter, a training-free model routing method designed to optimize the synergy among multiple LLMs for open-domain text generation tasks. Experimental results demonstrate that TagRouter outperforms 13 baseline methods, increasing the accept rate of system by 6.15% and reducing costs by 17.20%, achieving optimal cost-efficiency. Our findings provides the LLM community with an efficient and scalable solution for model ensembling, offering users an evolvable "super model."

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 34 of its 55 references that are in the map. First posted on arXiv 14 Jun 2025.

Builds on

34 of 55 references.

References · 34

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  5. 2020Scaling Laws for Neural Language Modelscited by 6,586
  6. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  7. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  8. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,653
  9. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,332
  10. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
  11. 2024DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Modelscited by 867
  12. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 853
22 more
  1. 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 682
  2. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 564
  3. 2023CMMLU: Measuring massive multitask language understanding in Chinesecited by 449
  4. 2024Hybrid LLM: Cost-Efficient and Quality-Aware Query Routingcited by 372
  5. 2020MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformerscited by 245
  6. 2023Speculative Decoding with Big Little Decodercited by 164
  7. 2023Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoningcited by 143
  8. 2023Fly-Swat or Cannon? Cost-Effective Language Model Choice via Meta-Modelingcited by 95
  9. 2024Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agentscited by 74
  10. 2024Controllable Text Generation for Large Language Models: A Surveycited by 57
  11. 2024Harnessing the Power of Multiple Minds: Lessons Learned from LLM Routingcited by 46
  12. 2021Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Explorationcited by 44
  13. 2024LLM-TOPLA: Efficient LLM Ensemble by Maximising Diversitycited by 42
  14. 2024MetaLLM: A High-performant and Cost-efficient Dynamic Framework for Wrapping LLMscited by 41
  15. 2023Trapping LLM Hallucinations Using Tagged Context Promptscited by 34
  16. 2024Routoo: Learning to Route to Large Language Models Effectivelycited by 34
  17. 2024Optimising Calls to Large Language Models with Uncertainty-Based Two-Tier Selectioncited by 33
  18. 2024Tag-LLM: Repurposing General-Purpose LLMs for Specialized Domainscited by 30
  19. 2024Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLMcited by 27
  20. 2024Purifying Large Language Models by Ensembling a Small Language Modelcited by 25
  21. 2023OrchestraLLM: Efficient Orchestration of Language Models for Dialogue State Trackingcited by 19
  22. 2025ClimateChat: Designing Data and Methods for Instruction Tuning LLMs to Answer Climate Change Queriescited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 6; 2026: 3.

9 papers.

  1. 2025Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Modelscited by 37
  2. 2025VL-RouterBench: A Benchmark for Vision-Language Model Routingcited by 8
  3. 2025RADAR: Reasoning-Ability and Difficulty-Aware Routing for Reasoning LLMscited by 6
  4. 2025ProxRouter: Proximity-Weighted LLM Query Routing for Improved Robustness to Outlierscited by 6
  5. 2025LLMRank: Understanding LLM Strengths for Model Routingcited by 4
  6. 2026Agentic Routing: The Harness-Native Data Flywheelcited by 4
  7. 2026Federate the Router: Learning Language Model Routers with Sparse and Decentralized Evaluationscited by 3
  8. 2025Routesplain: Towards Faithful and Intervenable Routing for Software-related Taskscited by 2
  9. 2026Routing Without Embeddings: Fast And Interpretable Routing With Regular Expressionscited by 0