Flexible Routing via Uncertainty Decomposition

• URL: http://arxiv.org/abs/2605.07805v1
• Date: Fri, 08 May 2026 14:39:57 GMT
• Title: Flexible Routing via Uncertainty Decomposition
• Abstract summary: Key strategy for balancing performance and cost in machine learning systems is to dynamically route queries to either a low-cost model or an expensive oracle.<n>We present a new uncertainty-aware router that avoids unnecessary oracle calls on inherently ambiguous queries.
• Score: 13.854691350572821
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A key strategy for balancing performance and cost in modern machine learning systems is to dynamically route queries to either a low-cost model or a more expensive oracle (such as a large pretrained model or human expert), an approach known as model routing. In this work we present a new uncertainty-aware router that (1) avoids unnecessary oracle calls on inherently ambiguous queries, and (2) adapts dynamically to different loss functions and cost parameters through simple hyperparameter changes, without retraining. Our method, applicable to any classification setting where multiple independent annotations per input are available, is based on decomposing total uncertainty into irreducible and reducible components using higher-order predictors [Ahdritz et al., 2025]. This enables a unified approach to both routing and abstention: predict with the weak model when uncertainty is low, route to the oracle when reducible uncertainty is high, and abstain when irreducible uncertainty is high. Our router comes with strong theoretical guarantees bounding regret relative to optimal task-specific routers. We conduct experiments on both synthetic and real-world datasets that demonstrate the benefits of our approach in suitable regimes -- in particular, whenever reducible and irreducible uncertainty are not too correlated.

Related papers

• Adaptive Smooth Tchebycheff Attention for Multi-Objective Policy Optimization [55.338784037660474]
  Multi- curvature reinforcement learning in domains requires balancing complex, non-fragile interference trade-offs between conflicting objectives.<n>In this paper we introduce a novel based real-time based real-time optimization on a robotic visual -- a proxy for monitoring ecosystems.
  arXiv  Detail & Related papers  (2026-05-12T21:32:57Z)
• Non-Parametric Rehearsal Learning via Conditional Mean Embeddings [88.89267783967263]
  We propose a non-parametric rehearsal learning approach for textitavoiding undesired future (AUF) problems.<n>Specifically, we use kernel machinery to reformulate the AUF objective into a unified representation that disentangles desirability modeling from action-induced distributional changes.
  arXiv  Detail & Related papers  (2026-05-09T15:30:52Z)
• Efficient and Interpretable Multi-Agent LLM Routing via Ant Colony Optimization [58.59491516762626]
  We propose AMRO-S, an efficient and interpretable routing framework for Multi-Agent Systems (MAS)<n>AMRO-S models MAS routing as a semantic-conditioned path selection problem, enhancing routing performance through three key mechanisms.<n>Extensive experiments on five public benchmarks and high-concurrency stress tests demonstrate that AMRO-S consistently improves the quality--cost trade-off over strong routing baselines.
  arXiv  Detail & Related papers  (2026-03-13T12:26:05Z)
• ODAR: Principled Adaptive Routing for LLM Reasoning via Active Inference [60.958331943869126]
  ODAR-Expert is an adaptive routing framework that optimize the accuracy-efficiency trade-off via principled resource allocation.<n>We show strong and consistent gains, including 98.2% accuracy on MATH and 54.8% on Humanity's Last Exam.
  arXiv  Detail & Related papers  (2026-02-27T05:22:01Z)
• How Robust Are Router-LLMs? Analysis of the Fragility of LLM Routing Capabilities [62.474732677086855]
  Large language model (LLM) routing has emerged as a crucial strategy for balancing computational costs with performance.<n>We propose the DSC benchmark: Diverse, Simple, and Categorized, an evaluation framework that categorizes router performance across a broad spectrum of query types.
  arXiv  Detail & Related papers  (2025-03-20T19:52:30Z)
• Stochastic Linear Bandits with Latent Heterogeneity [8.981251210938787]
  We propose a novel latent heterogeneous bandit framework that explicitly models this unobserved heterogeneity in customer responses.<n>Our methodology introduces an innovative algorithm that simultaneously learns latent group memberships and group-specific reward functions.
  arXiv  Detail & Related papers  (2025-02-01T13:02:21Z)
• Online Learning under Budget and ROI Constraints via Weak Adaptivity [57.097119428915796]
  Existing primal-dual algorithms for constrained online learning problems rely on two fundamental assumptions. We show how such assumptions can be circumvented by endowing standard primal-dual templates with weakly adaptive regret minimizers. We prove the first best-of-both-worlds no-regret guarantees which hold in absence of the two aforementioned assumptions.
  arXiv  Detail & Related papers  (2023-02-02T16:30:33Z)
• Improve Noise Tolerance of Robust Loss via Noise-Awareness [60.34670515595074]
  We propose a meta-learning method which is capable of adaptively learning a hyper parameter prediction function, called Noise-Aware-Robust-Loss-Adjuster (NARL-Adjuster for brevity) Four SOTA robust loss functions are attempted to be integrated with our algorithm, and comprehensive experiments substantiate the general availability and effectiveness of the proposed method in both its noise tolerance and performance.
  arXiv  Detail & Related papers  (2023-01-18T04:54:58Z)
• Robust Neural Regression via Uncertainty Learning [5.654198773446211]
  Deep neural networks tend to underestimate uncertainty and produce overly confident predictions. We propose a simple solution by extending the time-tested iterative reweighted least square (IRLS) in generalised linear regression. We use two sub-networks to parametrise the prediction and uncertainty estimation, enabling easy handling of complex inputs and nonlinear response.
  arXiv  Detail & Related papers  (2021-10-12T23:19:13Z)
• Online Optimization and Ambiguity-based Learning of Distributionally Uncertain Dynamic Systems [1.6709415233613623]
  This paper proposes a novel approach to construct data-driven online solutions to optimization problems (P) subject to a class of distributionally uncertain dynamical systems. The introduced framework allows for the simultaneous learning of distributional system uncertainty via a parameterized, control-dependent ambiguity set. We also introduce an online version of Nesterov's accelerated-gradient algorithm, and analyze its performance to solve this class of problems via dissipativity theory.
  arXiv  Detail & Related papers  (2021-02-18T01:49:06Z)
• Learning Adaptive Loss for Robust Learning with Noisy Labels [59.06189240645958]
  Robust loss is an important strategy for handling robust learning issue. We propose a meta-learning method capable of robust hyper tuning. Four kinds of SOTA loss functions are attempted to be minimization, general availability and effectiveness.
  arXiv  Detail & Related papers  (2020-02-16T00:53:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.