用结构化框架统一评估与路由大模型请求，降本提效。
SEAR: Schema-Based Evaluation and Routing for LLM Gateways
- 构建可扩展的数据库模式，整合评估信号与运行指标
- 通过多阶段生成实现高质量结构化输出，准确率高
- 支持可解释路由，适合生产环境多模型调度
评估生产级大模型响应并跨提供商路由请求，需细粒度质量信号和可操作决策。针对这一空白，我们提出SEAR——一种面向多模型、多提供商大模型网关的基于模式的评估与路由系统。SEAR定义了一个可扩展的关系模式，涵盖大模型评估信号（上下文、意图、响应特征、问题归因、质量评分）和网关运行指标（延迟、成本、吞吐量），包含约一百个类型化、可执行SQL查询的字段，并建立跨表一致性关联。为可靠填充评估信号，SEAR提出自包含信号指令、在模式内推理及多阶段生成，生成可直接入库的结构化输出。由于信号通过大模型推理而非浅层分类器获得，SEAR能捕捉复杂请求语义，支持人类可读的路由解释，并在单一查询层统一评估与路由。在数千次生产会话中，SEAR在人工标注数据上表现优异，支持实际路由决策，实现显著降本且保持相近质量。
原文摘要 · Abstract (English)
Evaluating production LLM responses and routing requests across providers in LLM gateways requires fine-grained quality signals and operationally grounded decisions. To address this gap, we present SEAR, a schema-based evaluation and routing system for multi-model, multi-provider LLM gateways. SEAR defines an extensible relational schema covering both LLM evaluation signals (context, intent, response characteristics, issue attribution, and quality scores) and gateway operational metrics (latency, cost, throughput), with cross-table consistency links across around one hundred typed, SQL-queryable columns. To populate the evaluation signals reliably, SEAR proposes self-contained signal instructions, in-schema reasoning, and multi-stage generation that produces database-ready structured outputs. Because signals are derived through LLM reasoning rather than shallow classifiers, SEAR captures complex request semantics, enables human-interpretable routing explanations, and unifies evaluation and routing in a single query layer. Across thousands of production sessions, SEAR achieves strong signal accuracy on human-labeled data and supports practical routing decisions, including large cost reductions with comparable quality.
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。