mlsanityData to 7 Oct 2026

ProxRouter: Proximity-Weighted LLM Query Routing for Improved Robustness to Outliers

arXiv 2510.09852 ↗First posted 10 Oct 2025cs.LG cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Large language model (LLM) query routers are critical to modern AI platforms as they seek to improve efficiency by assigning inference queries to accurate, yet low-cost models. Parametric routers typically use trained neural networks for LLM selection but suffer from retraining and maintenance overheads. Nonparametric routers are training-free, instead estimating LLM accuracy and cost via similarity between encodings of the input query and training set queries. However, like their parametric counterparts, nonparametric routers struggle to generalize to outlier queries, an issue exacerbated by limited diversity in training sets which are costly to expand and difficult to keep current with ever-evolving use cases. We propose ProxRouter, which applies an exponentially tilted aggregation mechanism to balance bias and variance in nonparametric routers, improving their robustness to outliers. Experiments show ProxRouter enhances outlier routing while preserving inlier performance with minimal overhead.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 39 of its 66 references that are in the map. First posted on arXiv 10 Oct 2025.

Builds on

39 of 66 references.

References · 39

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  5. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  6. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  7. 2020Scaling Laws for Neural Language Modelscited by 6,411
  8. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  9. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  10. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  11. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,018
  12. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,883
27 more
  1. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  2. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,767
  3. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,615
  4. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,414
  5. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,324
  6. 2024Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preferencecited by 1,151
  7. 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 973
  8. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 861
  9. 2017Crowdsourcing Multiple Choice Science Questionscited by 742
  10. 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 633
  11. 2018Universal Sentence Encodercited by 485
  12. 2024GraphRouter: A Graph-based Router for LLM Selectionscited by 154
  13. 2023Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Modelscited by 141
  14. 2024RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Modelscited by 84
  15. 2025Universal Model Routing for Efficient LLM Inferencecited by 80
  16. 2024A Unified Approach to Routing and Cascading for LLMscited by 71
  17. 2025BEST-Route: Adaptive LLM Routing with Test-Time Optimal Computecited by 63
  18. 2024TensorOpera Router: A Multi-Model Router for Efficient LLM Inferencecited by 59
  19. 2025RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMscited by 58
  20. 2025IRT-Router: Effective and Interpretable Multi-LLM Routing via Item Response Theorycited by 40
  21. 2025The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giantscited by 37
  22. 2024Eagle: Efficient Training-Free Router for Multi-LLM Inferencecited by 34
  23. 2025LLM Bandit: Cost-Efficient LLM Generation via Preference-Conditioned Dynamic Routingcited by 32
  24. 2025Beyond GPT-5: Making LLMs Cheaper and Better via Performance-Efficiency Optimized Routingcited by 32
  25. 2025Prompt-to-Leaderboardcited by 27
  26. 2025TagRouter: Learning Route to LLMs through Tags for Open-Domain Text Generation Taskscited by 9
  27. 2025Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routerscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routingcited by 35
  2. 2026Federate the Router: Learning Language Model Routers with Sparse and Decentralized Evaluationscited by 3
  3. 2026Not All Turns Are Equally Hard: Adaptive Thinking Budgets For Efficient Multi-Turn Reasoning in Agentscited by 3
  4. 2026LOCUS: Low-Dimensional Model Embeddings for Efficient Model Exploration, Comparison, and Selectioncited by 2
  5. 2026Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloadscited by 0