自动发现细粒度任务类型，让大模型按需选型更准更省。
Scalable Prompt Routing via Fine-Grained Latent Task Discovery
- 用图聚类自动挖掘隐藏任务类型，替代人工分类。
- 在10个基准上优于所有单模型，成本不到一半。
- 适合大规模模型池的智能调度，提升效率与性价比。
提示路由通过动态从候选模型池中选择最适配的大型语言模型，以优化性能并控制成本。当模型池扩展至包含十余个前沿模型且性能差异微小时，现有方法面临挑战：人工定义的任务分类无法捕捉细微能力差异，而单一路由器难以区分多样化任务间的细微差别。本文提出两阶段路由架构，通过自动化细粒度任务发现与任务感知的质量评估解决上述问题。第一阶段采用基于图的聚类方法发现潜在任务类型，并训练分类器将提示分配至对应任务；第二阶段使用专家混合（Mixture-of-Experts）架构，配备任务特定的预测头进行专业化质量估计。推理时，融合两阶段预测结果，在任务级稳定性与提示级适应性间取得平衡。在10个基准和11个前沿模型上的评估显示，该方法持续优于现有基线，超越最强单模型表现，同时成本低于其一半。
原文摘要 · Abstract (English)
Prompt routing dynamically selects the most appropriate large language model from a pool of candidates for each query, optimizing performance while managing costs. As model pools scale to include dozens of frontier models with narrow performance gaps, existing approaches face significant challenges: manually defined task taxonomies cannot capture fine-grained capability distinctions, while monolithic routers struggle to differentiate subtle differences across diverse tasks. We propose a two-stage routing architecture that addresses these limitations through automated fine-grained task discovery and task-aware quality estimation. Our first stage employs graph-based clustering to discover latent task types and trains a classifier to assign prompts to discovered tasks. The second stage uses a mixture-of-experts architecture with task-specific prediction heads for specialized quality estimates. At inference, we aggregate predictions from both stages to balance task-level stability with prompt-specific adaptability. Evaluated on 10 benchmarks with 11 frontier models, our method consistently outperforms existing baselines and surpasses the strongest individual model while incurring less than half its cost.
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。