mlsanityData to 14 Oct 2026

CopRoute: Dependence-Aware Conformal Routing for Language Models

arXiv 2610.13276 ↗First posted 9 Oct 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Set-based language model routing aims to increase the coverage of the event where at least one model answers a query correctly while controlling the number of inference calls made. Existing risk-controlled routing policies bound the all-miss risk (the probability that every model in the selected set fails) by calibrating a single conformal threshold and applying it to a nested family of model sets. Because each model is scored in isolation, these policies ignore the dependence structure of model failures. Models that share training data or architecture tend to fail on the same queries, so two individually strong models can be jointly redundant while a weaker but complementary model covers the queries that the others miss. To account for this dependence, which existing risk-controlled policies ignore, we propose CopRoute, which orders models by how many new queries each one answers correctly beyond those already selected, decides per query how far down that order to go, and then picks the smallest cutoff that still meets the target risk. We show that CopRoute's ordering attains, on the design data, the best guarantee any efficient fixed-ordering algorithm can give for the average number of calls to the first correct model, and that a separate calibration step certifies the all-miss risk of the deployed sets. On RouterBench and RouterEval, CopRoute attains the fewest certified calls on nine of ten datasets at a target risk of 0.05 and on eight of ten at 0.10, making up to 79 percent fewer calls (median 24 percent) than the state-of-the-art risk-controlled policy at the same certified all-miss risk.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 42 of its 58 references that are in the map. First posted on arXiv 9 Oct 2026.

Builds on

42 of 58 references.

References · 42

  1. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  2. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 853
  3. 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 682
  4. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 564
  5. 2024Mixture-of-Agents Enhances Large Language Model Capabilitiescited by 438
  6. 2020Classification with Valid and Adaptive Coveragecited by 396
  7. 2024Hybrid LLM: Cost-Efficient and Quality-Aware Query Routingcited by 372
  8. 2020Uncertainty Sets for Image Classifiers using Conformal Predictioncited by 366
  9. 2022Conformal Risk Controlcited by 299
  10. 2021Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Controlcited by 271
  11. 2024RouterBench: A Benchmark for Multi-LLM Routing Systemcited by 238
  12. 2023Large Language Model Routing with Benchmark Datasetscited by 172
30 more
  1. 2023Conformal Language Modelingcited by 170
  2. 2018Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Samplingcited by 169
  3. 2024GraphRouter: A Graph-based Router for LLM Selectionscited by 165
  4. 2023Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Modelscited by 145
  5. 2023Conformal Prediction with Large Language Models for Multi-Choice Question Answeringcited by 139
  6. 2024Language Model Cascades: Token-level uncertainty and beyondcited by 121
  7. 2022Language Model Cascadescited by 107
  8. 2024RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Modelscited by 88
  9. 2024A Unified Approach to Routing and Cascading for LLMscited by 80
  10. 2025BEST-Route: Adaptive LLM Routing with Test-Time Optimal Computecited by 67
  11. 2025RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMscited by 61
  12. 2025Great Models Think Alike and this Undermines AI Oversightcited by 58
  13. 2024EmbedLLM: Learning Compact Representations of Large Language Modelscited by 48
  14. 2024Harnessing the Power of Multiple Minds: Lessons Learned from LLM Routingcited by 46
  15. 2024Cost-Effective Online Multi-LLM Selection with Versatile Reward Modelscited by 39
  16. 2025LLM Bandit: Cost-Efficient LLM Generation via Preference-Conditioned Dynamic Routingcited by 34
  17. 2014Learning the Parameters of Determinantal Point Process Kernelscited by 23
  18. 2025Doing More with Less: A Survey on Routing Strategies for Resource Optimisation in Large Language Model-Based Systemscited by 20
  19. 2025CP-Router: An Uncertainty-Aware Router Between LLM and LRMcited by 20
  20. 2024Prune 'n Predict: Optimizing LLM Decision-making with Conformal Predictioncited by 18
  21. 2017Faster Greedy MAP Inference for Determinantal Point Processescited by 15
  22. 2025Learning to Route LLMs from Bandit Feedback: One Policy, Many Trade-offscited by 15
  23. 2026When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Modelscited by 13
  24. 2026Don't Always Pick the Highest-Performing Model: An Information Theoretic View of LLM Ensemble Selectioncited by 11
  25. 2026RACER: Risk-Aware Calibrated Efficient Routing for Large Language Modelscited by 7
  26. 2025Valid Selection among Conformal Setscited by 5
  27. 2026Mixture of Complementary Agents for Robust LLM Ensemblecited by 3
  28. 2026Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routingcited by 3
  29. 2026CR^2: Cost-Aware Risk-Controlled Routing for Wireless Device-Edge LLM Inferencecited by 1
  30. 2026FlexRouter: Learning Complementary Model Sets for Flexible LLM Routingcited by 1

Built on by

Not cited yet.