Image de couverture de livre

When Routing Collapses: On the Degenerate Convergence of LLM Routers

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Lai, Guannan, Ye, Han-Jia
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

MMR-Bench: A Comprehensive Benchmark for Multimodal LLM Routing
par: Ma, Haoxuan, et autres
Publié: (2026)

ICL-Router: In-Context Learned Model Representations for LLM Routing
par: Wang, Chenxu, et autres
Publié: (2025)

Life-Cycle Routing Vulnerabilities of LLM Router
par: Lin, Qiqi, et autres
Publié: (2025)

RouterBench: A Benchmark for Multi-LLM Routing System
par: Hu, Qitian Jason, et autres
Publié: (2024)

When to Reason: Semantic Router for vLLM
par: Wang, Chen, et autres
Publié: (2025)

IRT-Router: Effective and Interpretable Multi-LLM Routing via Item Response Theory
par: Song, Wei, et autres
Publié: (2025)

GraphRouter: A Graph-based Router for LLM Selections
par: Feng, Tao, et autres
Publié: (2024)

ProxRouter: Proximity-Weighted LLM Query Routing for Improved Robustness to Outliers
par: Patel, Shivam, et autres
Publié: (2025)

vLLM Semantic Router: Signal Driven Decision Routing for Mixture-of-Modality Models
par: Liu, Xunzhuo, et autres
Publié: (2026)

ACE-Router: Generalizing History-Aware Routing from MCP Tools to the Agent Web
par: Yao, Zhiyuan, et autres
Publié: (2026)

SecureRouter: Encrypted Routing for Efficient Secure Inference
par: Zhang, Yukuan, et autres
Publié: (2026)

When Attention Collapses: How Degenerate Layers in LLMs Enable Smaller, Stronger Models
par: Sanyal, Sunny, et autres
Publié: (2024)

TCAndon-Router: Adaptive Reasoning Router for Multi-Agent Collaboration
par: Zhao, Jiuzhou, et autres
Publié: (2026)

TensorOpera Router: A Multi-Model Router for Efficient LLM Inference
par: Stripelis, Dimitris, et autres
Publié: (2024)

Mixture of Routers
par: Zhang, Jia-Chen, et autres
Publié: (2025)

MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents
par: Hu, Tianyu, et autres
Publié: (2026)

RouterRetriever: Routing over a Mixture of Expert Embedding Models
par: Lee, Hyunji, et autres
Publié: (2024)

LLM-Powered AI Agent Systems and Their Applications in Industry
par: Liang, Guannan, et autres
Publié: (2025)

Capability Instruction Tuning: A New Paradigm for Dynamic LLM Routing
par: Zhang, Yi-Kai, et autres
Publié: (2025)

RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory
par: Liu, Jun, et autres
Publié: (2025)

LightRouter: Towards Efficient LLM Collaboration with Minimal Overhead
par: Zhang, Yifan, et autres
Publié: (2025)

Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization
par: Tang, Haochun, et autres
Publié: (2026)

QAP-Router: Tackling Qubit Routing as Dynamic Quadratic Assignment with Reinforcement Learning
par: Nguyen, Kien X., et autres
Publié: (2026)

RadialRouter: Structured Representation for Efficient and Robust Large Language Models Routing
par: Jin, Ruihan, et autres
Publié: (2025)

Route-and-Reason: Scaling Large Language Model Reasoning with Reinforced Model Router
par: Shao, Chenyang, et autres
Publié: (2025)

One Router to Route Them All: Homogeneous Expert Routing for Heterogeneous Graph Transformers
par: Shakirov, Georgiy, et autres
Publié: (2025)

OrcaRouter: A Production-Oriented LLM Router with Hybrid Offline-Online Learning
par: Bao, Zhenghua, et autres
Publié: (2026)

AlphaRouter: Quantum Circuit Routing with Reinforcement Learning and Tree Search
par: Tang, Wei, et autres
Publié: (2024)

VL-RouterBench: A Benchmark for Vision-Language Model Routing
par: Huang, Zhehao, et autres
Publié: (2025)

Performance Characterization of Expert Router for Scalable LLM Inference
par: Pichlmeier, Josef, et autres
Publié: (2024)

VideoRouter: Query-Adaptive Dual Routing for Efficient Long-Video Understanding
par: Lin, Kuanwei, et autres
Publié: (2026)

MViewRouter: Internalizing Geometric Equivariance via Multi-view Alternating Attention for Combinatorial Routing
par: Liu, Shiyan, et autres
Publié: (2026)

Towards Fair and Comprehensive Evaluation of Routers in Collaborative LLM Systems
par: Wu, Wanxing, et autres
Publié: (2026)

SinkRouter: Sink-Aware Routing for Efficient Long-Context Decoding in Large Language and Multimodal Models
par: Liu, Junnan, et autres
Publié: (2026)

GraphRAG-Router: Learning Cost-Efficient Routing over GraphRAGs and LLMs with Reinforcement Learning
par: Fan, Dongzhe, et autres
Publié: (2026)

RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs
par: Huang, Zhongzhan, et autres
Publié: (2025)

ThinkRouter: Efficient Reasoning via Routing Thinking between Latent and Discrete Spaces
par: Xu, Xin, et autres
Publié: (2026)

Lodestar: An Online-Learning LLM Inference Router
par: Lim, Gangmuk, et autres
Publié: (2026)

Router-Suggest: Dynamic Routing for Multimodal Auto-Completion in Visually-Grounded Dialogs
par: Mishra, Sandeep, et autres
Publié: (2026)

Retrieval Collapses When AI Pollutes the Web
par: Yu, Hongyeon, et autres
Publié: (2026)