TURA：面向人工智能搜索的工具增强统一检索代理
TURA: Tool-Augmented Unified Retrieval Agent for AI Search
AI总结：
TURA通过结合RAG与代理工具使用，首次系统性地弥合静态RAG与动态信息源之间的差距，提升人工智能搜索的实时性和准确性。
摘要：
大型语言模型（LLMs）的出现正在将搜索引擎转变为对话式人工智能搜索产品，主要通过在网页语料库上使用检索增强生成（RAG）技术。然而，这种范式存在显著的工业限制。传统RAG方法在满足实时需求和需要访问动态生成内容（如票务可用性或库存）的结构化查询方面存在困难。受限于对静态页面的索引，搜索引擎无法执行此类时间敏感数据所需的交互式查询。学术研究主要集中在优化RAG用于静态内容，忽略了复杂意图和对数据库和实时API等动态来源的需求。为填补这一差距，我们引入TURA（面向人工智能搜索的工具增强统一检索代理），一种新的三阶段框架，结合RAG与代理工具使用，以访问静态内容和动态实时信息。TURA有三个关键组件：一个意图感知检索模块，用于分解查询并检索封装为模型上下文协议（MCP）服务器的信息源，一个基于有向无环图（DAG）的任务规划器，将任务依赖性建模为DAG以实现最优并行执行，以及一个轻量级的Distilled Agent执行器，用于高效的工具调用。TURA是首个系统地弥合静态RAG与动态信息源之间差距的架构，适用于世界级人工智能搜索产品。服务数千万用户，它利用代理框架提供稳健的实时答案，同时满足大规模工业系统低延迟需求。
英文摘要：
The advent of Large Language Models (LLMs) is transforming search engines into conversational AI search products, primarily using Retrieval-Augmented Generation (RAG) on web corpora. However, this paradigm has significant industrial limitations. Traditional RAG approaches struggle with real-time needs and structured queries that require accessing dynamically generated content like ticket availability or inventory. Limited to indexing static pages, search engines cannot perform the interactive queries needed for such time-sensitive data. Academic research has focused on optimizing RAG for static content, overlooking complex intents and the need for dynamic sources like databases and real-time APIs. To bridge this gap, we introduce TURA (Tool-Augmented Unified Retrieval Agent for AI Search), a novel three-stage framework that combines RAG with agentic tool-use to access both static content and dynamic, real-time information. TURA has three key components: an Intent-Aware Retrieval module to decompose queries and retrieve information sources encapsulated as Model Context Protocol (MCP) Servers, a DAG-based Task Planner that models task dependencies as a Directed Acyclic Graph (DAG) for optimal parallel execution, and a lightweight Distilled Agent Executor for efficient tool calling. TURA is the first architecture to systematically bridge the gap between static RAG and dynamic information sources for a world-class AI search product. Serving tens of millions of users, it leverages an agentic framework to deliver robust, real-time answers while meeting the low-latency demands of a large-scale industrial system.
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。
