Cover Image

LightRouter: Towards Efficient LLM Collaboration with Minimal Overhead

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Yifan, Zhao, Xinkui, Wang, Zuxin, Cheng, Guanjie, Xu, Yueshen, Deng, Shuiguang, Yin, Jianwei
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SortingHat: Redefining Operating Systems Education with a Tailored Digital Teaching Assistant
by: Zhang, Yifan, et al.
Published: (2026)

Walking the Schrödinger Bridge: A Direct Trajectory for Text-to-3D Generation
by: Li, Ziying, et al.
Published: (2025)

Video-QTR: Query-Driven Temporal Reasoning Framework for Lightweight Video Understanding
by: Zhao, Xinkui, et al.
Published: (2025)

Integrating Artificial Intelligence into Operating Systems: A Survey on Techniques, Applications, and Future Directions
by: Zhang, Yifan, et al.
Published: (2024)

A Robust Incomplete Multimodal Low-Rank Adaptation Approach for Emotion Recognition
by: Zhao, Xinkui, et al.
Published: (2025)

Completion by Comprehension: Guiding Code Generation with Multi-Granularity Understanding
by: Zhao, Xinkui, et al.
Published: (2025)

LSHFed: Robust and Communication-Efficient Federated Learning with Locally-Sensitive Hashing Gradient Mapping
by: Cheng, Guanjie, et al.
Published: (2025)

Is Collaboration Worth It? A Decision-Oriented Survey in Multi-Agent Systems
by: Cheng, Guanjie, et al.
Published: (2026)

DyC-STG: Dynamic Causal Spatio-Temporal Graph Network for Real-time Data Credibility Analysis in IoT
by: Cheng, Guanjie, et al.
Published: (2025)

AME: An Efficient Heterogeneous Agentic Memory Engine for Smartphones
by: Zhao, Xinkui, et al.
Published: (2025)

TRAIL: Joint Inference and Refinement of Knowledge Graphs with Large Language Models
by: Zhao, Xinkui, et al.
Published: (2025)

Next-Gen Computing Systems with Compute Express Link: a Comprehensive Survey
by: Chen, Chen, et al.
Published: (2024)

ProMAS: Proactive Error Forecasting for Multi-Agent Systems Using Markov Transition Dynamics
by: Zhao, Xinkui, et al.
Published: (2026)

Towards Fair and Comprehensive Evaluation of Routers in Collaborative LLM Systems
by: Wu, Wanxing, et al.
Published: (2026)

TCAndon-Router: Adaptive Reasoning Router for Multi-Agent Collaboration
by: Zhao, Jiuzhou, et al.
Published: (2026)

Quality-Aware Robust Multi-View Clustering for Heterogeneous Observation Noise
by: Wu, Peihan, et al.
Published: (2026)

HORAE: A Domain-Agnostic Language for Automated Service Regulation
by: Sun, Yutao, et al.
Published: (2024)

GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts
by: Zeng, Wenhao, et al.
Published: (2026)

IRT-Router: Effective and Interpretable Multi-LLM Routing via Item Response Theory
by: Song, Wei, et al.
Published: (2025)

TensorOpera Router: A Multi-Model Router for Efficient LLM Inference
by: Stripelis, Dimitris, et al.
Published: (2024)

Revisiting Vulnerability Patch Localization: An Empirical Study and LLM-Based Solution
by: Xu, Haoran, et al.
Published: (2025)

GraphRouter: A Graph-based Router for LLM Selections
by: Feng, Tao, et al.
Published: (2024)

GRAB-ANNS: High-Throughput Indexing and Hybrid Search via GPU-Native Bucketing
by: Zhao, Xinkui, et al.
Published: (2026)

StackPilot: Autonomous Function Agents for Scalable and Environment-Free Code Execution
by: Zhao, Xinkui, et al.
Published: (2025)

Role-Based Fault Tolerance System for LLM RL Post-Training
by: Chen, Zhenqian, et al.
Published: (2025)

TenonOS: A Self-Generating LibOS-on-LibOS Framework for Time-Critical Embedded Operating Systems
by: Zhao, Xinkui, et al.
Published: (2025)

RIPRAG: Hack a Black-box Retrieval-Augmented Generation Question-Answering System with Reinforcement Learning
by: Xi, Meng, et al.
Published: (2025)

HijackRAG: Hijacking Attacks against Retrieval-Augmented Large Language Models
by: Zhang, Yucheng, et al.
Published: (2024)

Lodestar: An Online-Learning LLM Inference Router
by: Lim, Gangmuk, et al.
Published: (2026)

Shiva-DiT: Residual-Based Differentiable Top-$k$ Selection for Efficient Diffusion Transformers
by: Zhang, Jiaji, et al.
Published: (2026)

Life-Cycle Routing Vulnerabilities of LLM Router
by: Lin, Qiqi, et al.
Published: (2025)

BPI: A Novel Efficient and Reliable Search Structure for Hybrid Storage Blockchain
by: Zhao, Xinkui, et al.
Published: (2025)

SRSA: A Cost-Efficient Strategy-Router Search Agent for Real-world Human-Machine Interactions
by: Wang, Yaqi, et al.
Published: (2024)

SatFusion: A Unified Framework for Enhancing Remote Sensing Images via Multi-Frame and Multi-Source Images Fusion
by: Tong, Yufei, et al.
Published: (2025)

ICL-Router: In-Context Learned Model Representations for LLM Routing
by: Wang, Chenxu, et al.
Published: (2025)

OrcaRouter: A Production-Oriented LLM Router with Hybrid Offline-Online Learning
by: Bao, Zhenghua, et al.
Published: (2026)

When Routing Collapses: On the Degenerate Convergence of LLM Routers
by: Lai, Guannan, et al.
Published: (2026)

Federated Data-Efficient Instruction Tuning for Large Language Models
by: Qin, Zhen, et al.
Published: (2024)

SecureRouter: Encrypted Routing for Efficient Secure Inference
by: Zhang, Yukuan, et al.
Published: (2026)

Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers
by: Ma, Wenhan, et al.
Published: (2025)