解决冷启动场景下大模型路由性能下降问题，通过构建任务谱系合成数据提升路由效果。
Task-Aware LLM Routing with Multi-Level Task-Profile-Guided Data Synthesis for Cold-Start Scenarios
- 构建多层级任务谱系，合成多样化问答对逼近真实查询分布
- 引入隐式任务类型变量建模查询条件下的成本与性能，支持冷启动和常规场景
- 适用于缺乏领域数据的新任务部署，尤其适合资源受限环境
大语言模型在不同任务和查询上的性能与计算开销差异显著，促使路由系统根据用户需求选择最优模型。然而，现有路由器在缺乏领域训练数据的冷启动场景下泛化能力差。本文提出一种多层级任务谱系引导的数据合成框架，构建层次化任务分类体系，并生成多样化的问答对以逼近测试时的查询分布。基于此，提出TRouter：一种任务类型感知的路由方法，通过潜在任务类型变量建模查询相关的成本与性能，并利用合成任务谱系作为先验正则化。该设计在冷启动和已有领域数据场景下均提升了路由效果。多个基准测试表明，该合成框架有效缓解冷启动问题，且TRouter实现了高效的LLM路由。
原文摘要 · Abstract (English)
Large language models (LLMs) exhibit substantial variability in performance and computational cost across tasks and queries, motivating routing systems that select models to meet user-specific cost-performance trade-offs. However, existing routers generalize poorly in cold-start scenarios where in-domain training data is unavailable. We address this limitation with a multi-level task-profile-guided data synthesis framework that constructs a hierarchical task taxonomy and produces diverse question-answer pairs to approximate the test-time query distribution. Building on this, we introduce TRouter, a task-type-aware router approach that models query-conditioned cost and performance via latent task-type variables, with prior regularization derived from the synthesized task taxonomy. This design enhances TRouter's routing utility under both cold-start and in-domain settings. Across multiple benchmarks, we show that our synthesis framework alleviates cold-start issues and that TRouter delivers effective LLM routing.
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。