让大模型自己决定该答还是转接，更灵活省钱。
DiSRouter: Distributed Self-Routing for LLM Selections
- 每个模型自主判断是否回答，无需中心调度
- 在多种任务上综合表现优于现有路由方法
- 适合构建可扩展的智能多模型协作系统
大型语言模型（LLMs）数量激增，性能与成本差异显著，亟需高效查询路由以平衡效果与开销。现有路由系统依赖固定模型集训练的集中式外部路由器，灵活性差且因小规模路由器难以理解各模型知识边界而表现不佳。本文提出DiSRouter（分布式自路由），将控制模式从集中转向分布式：查询在由多个具备自知能力的模型代理组成的网络中流转，每个代理根据自身能力独立判断是否回答或转发给其他代理。为此，我们设计了两阶段自知训练流程，提升各模型的自我评估能力。大量实验表明，DiSRouter在多种场景下显著优于现有路由方法，能有效区分简单与复杂问题，并对域外任务展现强泛化能力。结果验证：利用模型内在自知比外部评估更有效，为构建模块化、高效的多智能体系统开辟新路径。
原文摘要 · Abstract (English)
The proliferation of Large Language Models (LLMs) has created a diverse ecosystem of models with highly varying performance and costs, necessitating effective query routing to balance performance and expense. Current routing systems often rely on a centralized external router trained on a fixed set of LLMs, making them inflexible and prone to poor performance since the small router can not fully understand the knowledge boundaries of different LLMs. We introduce DiSRouter (Distributed Self-Router), a novel paradigm that shifts from centralized control to distributed routing. In DiSRouter, a query traverses a network of LLM agents, each independently deciding whether to answer or route to other agents based on its own self-awareness, its ability to judge its competence. This distributed design offers superior flexibility, scalability, and generalizability. To enable this, we propose a two-stage Self-Awareness Training pipeline that enhances each LLM's self-awareness. Extensive experiments demonstrate that DiSRouter significantly outperforms existing routing methods in utility across various scenarios, effectively distinguishes between easy and hard queries, and shows strong generalization to out-of-domain tasks. Our work validates that leveraging an LLM's intrinsic self-awareness is more effective than external assessment, paving the way for more modular and efficient multi-agent systems.
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。