mlsanityData to 14 Oct 2026

GraphRouter: A Graph-based Router for LLM Selections

arXiv 2410.03834 ↗First posted 4 Oct 2024cs.AIcited by 165

Not on the map. Why?

Cited by 32 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The rapidly growing number and variety of Large Language Models (LLMs) present significant challenges in efficiently selecting the appropriate LLM for a given query, especially considering the trade-offs between performance and computational cost. Current LLM selection methods often struggle to generalize across new LLMs and different tasks because of their limited ability to leverage contextual interactions among tasks, queries, and LLMs, as well as their dependence on a transductive learning framework. To address these shortcomings, we introduce a novel inductive graph framework, named as GraphRouter, which fully utilizes the contextual information among tasks, queries, and LLMs to enhance the LLM selection process. GraphRouter constructs a heterogeneous graph comprising task, query, and LLM nodes, with interactions represented as edges, which efficiently captures the contextual information between the query's requirements and the LLM's capabilities. Through an innovative edge prediction mechanism, GraphRouter is able to predict attributes (the effect and cost of LLM response) of potential edges, allowing for optimized recommendations that adapt to both existing and newly introduced LLMs without requiring retraining. Comprehensive experiments across three distinct effect-cost weight scenarios have shown that GraphRouter substantially surpasses existing routers, delivering a minimum performance improvement of 12.3%. In addition, it achieves enhanced generalization across new LLMs settings and supports diverse tasks with at least a 9.5% boost in effect and a significant reduction in computational demands. This work endeavors to apply a graph-based approach for the contextual and adaptive selection of LLMs, offering insights for real-world applications. Our codes for GraphRouter is released at https://github.com/ulab-uiuc/GraphRouter.

Key facts. Cited by 165 papers in the map (data through 14 Oct 2026). Builds on 41 of its 53 references that are in the map. First posted on arXiv 4 Oct 2024.

Builds on

41 of 53 references.

References · 41

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  5. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  6. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  7. 2017Graph Attention Networkscited by 8,923
  8. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  9. 2017Inductive Representation Learning on Large Graphscited by 6,320
  10. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  11. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  12. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
29 more
  1. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  2. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,181
  3. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  4. 2022Large Language Models Encode Clinical Knowledgecited by 1,830
  5. 2024Mixtral of Expertscited by 1,823
  6. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  7. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,392
  8. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 853
  9. 2019Heterogeneous Graph Attention Networkcited by 734
  10. 2020Heterogeneous Graph Transformercited by 582
  11. 2022BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Miningcited by 538
  12. 2020Graph Neural Networks in Recommender Systems: A Surveycited by 494
  13. 2019Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Modelcited by 431
  14. 2024Hybrid LLM: Cost-Efficient and Quality-Aware Query Routingcited by 372
  15. 2024Large Language Models for Mathematical Reasoning: Progresses and Challengescited by 284
  16. 2023MathPrompter: Mathematical Reasoning using Large Language Modelscited by 236
  17. 2023NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classificationcited by 210
  18. 2023Fly-Swat or Cannon? Cost-Effective Language Model Choice via Meta-Modelingcited by 95
  19. 2023Relational Deep Learning: Graph Representation Learning on Relational Databasescited by 56
  20. 2024What is the Role of Small Models in the LLM Era: A Surveycited by 41
  21. 2021ConsisRec: Enhancing GNN for Social Recommendation via Consistent Neighbor Aggregationcited by 39
  22. 2024Cost-Effective Online Multi-LLM Selection with Versatile Reward Modelscited by 39
  23. 2023TCRA-LLM: Token Compression Retrieval Augmented Large Language Model for Inference Cost Reductioncited by 34
  24. 2024PyBench: Evaluating LLM Agent on various real-world coding taskscited by 24
  25. 2019Fine-grained Event Categorization with Heterogeneous Graph Convolutional Networkscited by 23
  26. 2023On Optimal Caching and Model Multiplexing for Large Model Inferencecited by 20
  27. 2021GraphHop: An Enhanced Label Propagation Method for Node Classificationcited by 15
  28. 2023Relational Multi-Task Learning: Modeling Relations between Data and Taskscited by 15
  29. 2024Studying LLM Performance on Closed- and Open-source Datacited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 62; 2026: 102.

165 papers.

Sort:

By area:

  1. 2025Multi-agent Architecture Search via Agentic Supernetcited by 179
  2. 2025MasRouter: Learning to Route LLMs for Multi-Agent Systemscited by 88
  3. 2025Universal Model Routing for Efficient LLM Inferencecited by 86
  4. 2025Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learningcited by 72
  5. 2025RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMscited by 61
  6. 2025Cache-to-Cache: Direct Semantic Communication Between Large Language Modelscited by 61
  7. 2025EvoFlow: Evolving Diverse Agentic Workflows On The Flycited by 55
  8. 2025IRT-Router: Effective and Interpretable Multi-LLM Routing via Item Response Theorycited by 40
  9. 2025The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giantscited by 38
  10. 2026LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routingcited by 38
  11. 2025Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Modelscited by 37
  12. 2025OmniRouter: Budget and Performance Controllable Multi-LLM Routingcited by 35
38 more
  1. 2025Beyond GPT-5: Making LLMs Cheaper and Better via Performance-Efficiency Optimized Routingcited by 34
  2. 2025When One LLM Drools, Multi-LLM Collaboration Rulescited by 28
  3. 2025Difficulty-Aware Agentic Orchestration for Query-Specific Multi-Agent Workflowscited by 27
  4. 2025Adaptive LLM Routing under Budget Constraintscited by 24
  5. 2025Route to Reason: Adaptive Routing for LLM and Reasoning Strategy Selectioncited by 23
  6. 2026SkillOrchestra: Learning to Route Agents via Skill Transfercited by 23
  7. 2025RouterArena: An Open Platform for Comprehensive Comparison of LLM Routerscited by 22
  8. 2025Leveraging Uncertainty Estimation for Efficient LLM Routingcited by 21
  9. 2025Doing More with Less: A Survey on Routing Strategies for Resource Optimisation in Large Language Model-Based Systemscited by 20
  10. 2025Ten Challenging Problems in Federated Foundation Modelscited by 20
  11. 2025Online Multi-LLM Selection via Contextual Bandits under Unstructured Context Evolutioncited by 19
  12. 2026Dynamic Model Routing and Cascading for Efficient LLM Inference: A Surveycited by 19
  13. 2025Murakkab: Resource-Efficient Agentic Workflow Orchestration in Cloud Platformscited by 18
  14. 2025Cost-Aware Contrastive Routing for LLMscited by 16
  15. 2026EvoRoute: Experience-Driven Self-Routing LLM Agent Systemscited by 16
  16. 2025Learning to Route LLMs from Bandit Feedback: One Policy, Many Trade-offscited by 15
  17. 2026EvolveRouter: Co-Evolving Routing and Prompt for Multi-Agent Question Answeringcited by 15
  18. 2026R2-Router: A New Paradigm for LLM Routing with Reasoningcited by 14
  19. 2025Route-and-Reason: Scaling Large Language Model Reasoning with Reinforced Model Routercited by 13
  20. 2025Semantic Caching for Low-Cost LLM Serving: From Offline Learning to Online Adaptationcited by 13
  21. 2025Efficient Training-Free Online Routing for High-Volume Multi-LLM Servingcited by 13
  22. 2026MMR-Bench: A Comprehensive Benchmark for Multimodal LLM Routingcited by 13
  23. 2026Learning Query-Aware Budget-Tier Routing for Runtime Agent Memorycited by 13
  24. 2025Mixture of Thoughts: Learning to Aggregate What Experts Think, Not Just What They Saycited by 12
  25. 2026GraphPlanner: Graph Memory-Augmented Agentic Routing for Multi-Agent LLMscited by 12
  26. 2025Life-Cycle Routing Vulnerabilities of LLM Routercited by 11
  27. 2025Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routerscited by 11
  28. 2025RadialRouter: Structured Representation for Efficient and Robust Large Language Models Routingcited by 11
  29. 2026SWE-Router: Routing in Multi-turn Agentic Software Engineering Taskscited by 11
  30. 2025FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Datacited by 10
  31. 2025Learning Compact Representations of LLM Abilities via Item Response Theorycited by 10
  32. 2025Don't Throw Away Your Pretrained Modelcited by 10
  33. 2026When Routing Collapses: On the Degenerate Convergence of LLM Routerscited by 10
  34. 2026Task-Aware LLM Routing with Multi-Level Task-Profile-Guided Data Synthesis for Cold-Start Scenarioscited by 10
  35. 2025Arch-Router: Aligning LLM Routing with Human Preferencescited by 9
  36. 2025RAGRouter: Learning to Route Queries to Multiple Retrieval-Augmented Language Modelscited by 8
  37. 2025VL-RouterBench: A Benchmark for Vision-Language Model Routingcited by 8
  38. 2026Ares: Adaptive Reasoning Effort Selection for Efficient LLM Agentscited by 8

50 most cited of 165 All 165 (JSON)