Image de couverture de livre

OmniRouter: Budget and Performance Controllable Multi-LLM Routing

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Mei, Kai, Xu, Wujiang, Guo, Minghao, Lin, Shuhang, Zhang, Yongfeng
Format:	Preprint
Publié:	2025
Sujets:	Databases Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

How Robust Are Router-LLMs? Analysis of the Fragility of LLM Routing Capabilities
par: Kassem, Aly M., et autres
Publié: (2025)

RouterKGQA: Specialized--General Model Routing for Constraint-Aware Knowledge Graph Question Answering
par: Yuan, Bo, et autres
Publié: (2026)

A-MEM: Agentic Memory for LLM Agents
par: Xu, Wujiang, et autres
Publié: (2025)

OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scale
par: Li, Haoyang, et autres
Publié: (2025)

BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute
par: Ding, Dujian, et autres
Publié: (2025)

Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework
par: Wu, Yanchen, et autres
Publié: (2026)

SQLStructEval: Structural Evaluation of LLM Text-to-SQL Generation
par: Zhou, Yixi, et autres
Publié: (2026)

HyperJoin: LLM-augmented Hypergraph Link Prediction for Joinable Table Discovery
par: Liu, Shiyuan, et autres
Publié: (2026)

From Commands to Prompts: LLM-based Semantic File System for AIOS
par: Shi, Zeru, et autres
Publié: (2024)

SEAR: Schema-Based Evaluation and Routing for LLM Gateways
par: Zhang, Zecheng, et autres
Publié: (2026)

MEBench: Benchmarking Large Language Models for Cross-Document Multi-Entity Question Answering
par: Lin, Teng, et autres
Publié: (2025)

Replacing Multi-Step Assembly of Data Preparation Pipelines with One-Step LLM Pipeline Generation for Table QA
par: Li, Fengyu, et autres
Publié: (2026)

SQLfuse: Enhancing Text-to-SQL Performance through Comprehensive LLM Synergy
par: Zhang, Tingkai, et autres
Publié: (2024)

DBCopilot: Natural Language Querying over Massive Databases via Schema Routing
par: Wang, Tianshu, et autres
Publié: (2023)

OmniPred: Language Models as Universal Regressors
par: Song, Xingyou, et autres
Publié: (2024)

Rethinking Text-to-SQL: Dynamic Multi-turn SQL Interaction for Real-world Database Exploration
par: Sun, Linzhuang, et autres
Publié: (2025)

iAgent: LLM Agent as a Shield between User and Recommender Systems
par: Xu, Wujiang, et autres
Publié: (2025)

ErrorLLM: Modeling SQL Errors for Text-to-SQL Refinement
par: Hong, Zijin, et autres
Publié: (2026)

LLM Router: Rethinking Routing with Prefill Activations
par: Varshney, Tanay, et autres
Publié: (2026)

Knapsack Optimization-based Schema Linking for LLM-based Text-to-SQL Generation
par: Yuan, Zheng, et autres
Publié: (2025)

ContextCache: Context-Aware Semantic Cache for Multi-Turn Queries in Large Language Models
par: Yan, Jianxin, et autres
Publié: (2025)

LLM as GNN: Graph Vocabulary Learning for Text-Attributed Graph Foundation Models
par: Zhu, Xi, et autres
Publié: (2025)

An LLM Agent-Based Complex Semantic Table Annotation Approach
par: Geng, Yilin, et autres
Publié: (2025)

LLM-SQL-Solver: Can LLMs Determine SQL Equivalence?
par: Zhao, Fuheng, et autres
Publié: (2023)

StorageXTuner: An LLM Agent-Driven Automatic Tuning Framework for Heterogeneous Storage Systems
par: Lin, Qi, et autres
Publié: (2025)

Multi-Meta-RAG: Improving RAG for Multi-Hop Queries using Database Filtering with LLM-Extracted Metadata
par: Poliakov, Mykhailo, et autres
Publié: (2024)

SMUTF: Schema Matching Using Generative Tags and Hybrid Features
par: Zhang, Yu, et autres
Publié: (2024)

LLMpedia: A Transparent Framework to Materialize an LLM's Encyclopedic Knowledge at Scale
par: Saeed, Muhammed, et autres
Publié: (2026)

EllieSQL: Cost-Efficient Text-to-SQL with Complexity-Aware Routing
par: Zhu, Yizhang, et autres
Publié: (2025)

Arch-Router: Aligning LLM Routing with Human Preferences
par: Tran, Co, et autres
Publié: (2025)

PM-LLM-Benchmark: Evaluating Large Language Models on Process Mining Tasks
par: Berti, Alessandro, et autres
Publié: (2024)

AutoDCWorkflow: LLM-based Data Cleaning Workflow Auto-Generation and Benchmark
par: Li, Lan, et autres
Publié: (2024)

MixLLM: Dynamic Routing in Mixed Large Language Models
par: Wang, Xinyuan, et autres
Publié: (2025)

FineWeb-zhtw: Scalable Curation of Traditional Chinese Text Data from the Web
par: Lin, Cheng-Wei, et autres
Publié: (2024)

Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding
par: Jin, Mingyu, et autres
Publié: (2025)

Individual Turing Test: A Case Study of LLM-based Simulation Using Longitudinal Personal Data
par: Guo, Minghao, et autres
Publié: (2026)

AEL: Agent Evolving Learning for Open-Ended Environments
par: Xu, Wujiang, et autres
Publié: (2026)

AIOS: LLM Agent Operating System
par: Mei, Kai, et autres
Publié: (2024)

TCM-Ladder: A Benchmark for Multimodal Question Answering on Traditional Chinese Medicine
par: Xie, Jiacheng, et autres
Publié: (2025)

LLM-R2: A Large Language Model Enhanced Rule-based Rewrite System for Boosting Query Efficiency
par: Li, Zhaodonghui, et autres
Publié: (2024)