TokenRouter: Efficient Serving System for Token-Level LLM Routing

arXiv:2610.12242 · cs.CL · Submitted 2026-10-08 · Read on arXiv

cs.CL

Submitted: 2026-10-08

Updated: 2026-10-08

Code: https://github.com/thu-nics/TokenRouter

Terminology

• Ablation — 5× in this paper · explained in 1 episode
• Decode — 5× in this paper · explained in 2 episodes
• Ablation study — 4× in this paper · explained in 1 episode
• Benchmark — 4× in this paper · explained in 2 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Adam — 3× in this paper · explained in 2 episodes
• Speculative Decoding — 3× in this paper · explained in 2 episodes
• Core — 2× in this paper · explained in 2 episodes
• Discrete-Time Markov Chain — 2× in this paper
• Transformer — 2× in this paper · explained in 2 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Agentic Task — 1× in this paper · explained in 1 episode
• Agentic Tasks — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Deferral — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 3 episodes
• Geometric Distribution — 1× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Service Level Objective — 1× in this paper
• Verification — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• OpenAI GPT-5 System Card
• RouteLLM: Learning to Route LLMs with Preference Data
• Think-at-Hard: Dynamic Looped Transformers for Improved Reasoning
• R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing
• RelayLLM: Efficient Reasoning via Collaborative Decoding
• Collaborative decoding of critical tokens for boosting factuality of large language models
• TARo: Token-level Adaptive Routing for LLM Test-time Alignment
• Token-Level LLM Collaboration via FusionRoute
• CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing
• Cache-to-Cache: Direct Semantic Communication Between Large Language Models
• FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
• Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing
• Eagle: Efficient Training-Free Router for Multi-LLM Inference
• RouterBench: A Benchmark for Multi-LLM Routing System
• RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs
• GraphRouter: A Graph-based Router for LLM Selections
• Mixture-of-Agents Enhances Large Language Model Capabilities
• ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration
• SplitReason: Learning To Offload Reasoning
• R-Stitch: Dynamic Trajectory Stitching for Efficient Reasoning

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering