Pathwise-Budgeted LLM Routing: Online Allocation with K-Bit Tail-Cost Learning
cs.LG, math.OC
Submitted: 2026-11-04
Updated: 2026-11-04
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Online Pandora's Box for Contextual LLM Cascading
- Learning to Route and Schedule LLMs from User Retrials via Contextual Queueing Bandits
- OR for AI That Does OR: Routing LLMs up the Escalator inside the OSCAR Framework
- RouterBench: A Benchmark for Multi-LLM Routing System
- Asymptotically Optimal Sequential Testing with Heterogeneous LLMs
- ParetoBandit: Budget-Paced Adaptive Routing for Non-Stationary LLM Serving
- Robust Length Prediction: A Perspective from Heavy-Tailed Prompt-Conditioned Distributions
- SeqRoute: Global Budget-Aware Sequential LLM Routing via Offline Reinforcement Learning
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis