TURA: Tool-Augmented Unified Retrieval Agent for AI Search

TL;DR

TURA is a novel framework that combines retrieval-augmented generation with agentic tool-use to access both static and real-time dynamic information sources, improving AI search capabilities for industrial applications.

Contribution

It introduces a three-stage architecture integrating static retrieval, task planning, and tool execution to handle complex, real-time queries in large-scale AI search systems.

Findings

Successfully serves tens of millions of users with real-time answers.

Bridges the gap between static RAG and dynamic data sources.

Enhances AI search with efficient, low-latency tool integration.

Abstract

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.