统一LLM路由框架，提升多场景下模型选择效率与成本控制。
LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers
- 将路由问题建模为五组件序列决策过程，支持单轮、多轮和个性化任务。
- 构建xRouteBench基准，覆盖多种任务类型，实测学习型路由相对基线提升14.6%。
- 开源模块化工具LLMRouter，适合研究者快速搭建与评估路由系统。
单一大型语言模型无法在所有查询和预算约束下表现最优，因此模型路由对低成本部署至关重要。现有路由方法形式多样、实现各异，导致公平比较与扩展困难。本文提出一种统一的LLM路由建模方式，将其视为由五个组件构成的序列决策过程：上下文编码器、模型编码器、打分函数、决策规则和学习信号，涵盖单轮、多轮及个性化路由。基于此，我们开发了一个自动化管道，用于生成路由监督信号并联合评估响应质量与推理成本。由此构建的基准xRouteBench覆盖通用LLM、记忆增强、视觉、时间序列及个性化路由任务。进一步提出LLMRouter，一个开源模块化基础设施，包含16种以上代表性路由器。实证研究表明，学习型路由相比最强固定模型基线相对提升14.6%，轻量级路由在严苛成本约束下更具竞争力，用户条件路由持续提升个性化效果。
原文摘要 · Abstract (English)
No single large language model (LLM) is optimal across all queries and budget constraints, making model routing essential for cost-effective deployment. Existing routers adopt diverse formulations and implementations, making fair comparison and extension difficult. We present a unified formulation of LLM routing as a sequential decision process characterized by five components: context encoders, model encoders, scoring functions, decision rules, and learning signals, covering single-turn, multi-turn, and personalized routing. Based on this formulation, we develop an automated pipeline for constructing routing supervision and evaluating routers jointly on response quality and inference cost. The resulting benchmark, xRouteBench, spans generic LLM, memory-augmented, vision, time-series, and personalized routing tasks. We further introduce LLMRouter, an open-source modular infrastructure with more than 16 representative routers. Our empirical study shows that learned routers outperform the strongest fixed-model baseline by 14.6% relatively, lightweight routers become more competitive under tight cost constraints, and user-conditioned routing consistently improves personalization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。