重新思考LLM路由的预测建模：当简单kNN胜过复杂学习路由
Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routers
AI总结：
本文通过简单性视角重新审视LLM路由，发现经过调优的kNN方法在多种任务中优于现有学习路由方法，引入标准化基准测试和多模态数据集，揭示嵌入空间局部性属性使非参数方法在样本复杂度更低的情况下实现强路由决策。
摘要：
随着大型语言模型（LLMs）规模和专业化程度的提升，路由——为给定输入选择最佳模型——已成为高效有效部署的关键。尽管最近的方法依赖于复杂的 learned routing 策略，但其对异质训练数据和评估设置的依赖使得比较和泛化变得困难。在本工作中，我们通过简单性视角重新审视 LLM 路由。我们展示，经过良好调优的 k-Nearest Neighbors（kNN）方法不仅匹配，而且在多种任务中经常优于最先进的 learned routers。为了支持系统的评估，我们引入了一套标准化的路由基准测试，涵盖指令遵循、问答和推理任务，以及第一个涉及视觉输入的多模态路由数据集。我们的发现揭示了嵌入空间中模型性能的局部性属性，使简单的非参数方法能够以比参数方法更低的样本复杂度实现强大的路由决策。这挑战了向复杂架构发展的主流趋势，并强调在投资复杂解决方案之前，必须彻底评估简单的基线。为了支持可重复性和进一步探索，我们将在发表时发布所有基准和代码。
英文摘要：
As large language models (LLMs) grow in scale and specialization, routing--selecting the best model for a given input--has become essential for efficient and effective deployment. While recent methods rely on complex learned routing strategies, their dependence on disparate training data and evaluation setups makes comparison and generalization difficult. In this work, we revisit LLM routing through the lens of simplicity. We show that a well-tuned k-Nearest Neighbors (kNN) approach not only matches but often outperforms state-of-the-art learned routers across diverse tasks. To support systematic evaluation, we introduce a suite of standardized routing benchmarks spanning instruction-following, question-answering, and reasoning tasks, as well as the first multi-modal routing dataset involving visual inputs. Our findings reveal that the locality properties of model performance in embedding space enable simple non-parametric methods to achieve strong routing decisions with lower sample complexity than parametric approaches. This challenges the prevailing trend toward sophisticated architectures and highlights the importance of thoroughly evaluating simple baselines before investing in complex solutions. To support reproducibility and further exploration, we will release all benchmarks and code upon publication.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
