mlsanityData to 14 Oct 2026

TURA: Tool-Augmented Unified Retrieval Agent for AI Search

arXiv 2508.04604 ↗First posted 6 Aug 2025cs.CL cs.AI cs.IRcited by 6

On the map: Retrieval-augmented generation → Agentic RAG, agents and memory

also in 1 more
Abstract (arXiv)

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.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation. Builds on 21 of its 47 references that are in the map. First posted on arXiv 6 Aug 2025.

Builds on

21 of 47 references.

References · 21

  1. 2025Qwen3 Technical Reportcited by 8,820
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  5. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  6. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  7. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 849
  8. 2024Executable Code Actions Elicit Better LLM Agentscited by 564
  9. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 452
  10. 2023ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Casescited by 393
  11. 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agentscited by 392
  12. 2024Agent Q: Advanced Reasoning and Learning for Autonomous AI Agentscited by 208
9 more
  1. 2023An LLM Compiler for Parallel Function Callingcited by 179
  2. 2023ADaPT: As-Needed Decomposition and Planning with Language Modelscited by 177
  3. 2024An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4cited by 94
  4. 2024Demystifying Chains, Trees, and Graphs of Thoughtscited by 63
  5. 2024Re-Invoke: Tool Invocation Rewriting for Zero-Shot Tool Retrievalcited by 52
  6. 2025Distilling LLM Agent into Small Models with Retrieval and Code Toolscited by 47
  7. 2025Magnet: Multi-turn Tool-use Data Synthesis and Distillation via Graph Translationcited by 37
  8. 2021Pre-trained Language Model based Ranking in Baidu Searchcited by 34
  9. 2024LLMs are Also Effective Embedding Models: An In-depth Overviewcited by 32

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 3.

6 papers.

  1. 2025A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applicationscited by 22
  2. 2025Beyond ReAct: A Planner-Centric Framework for Complex Tool-Augmented LLM Reasoningcited by 17
  3. 2026SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directionscited by 8
  4. 2026AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Securitycited by 8
  5. 2026Dense Process Supervision for Search Agents via Fact Utility Estimationcited by 1
  6. 2025Z-Space: A Multi-Agent Tool Orchestration Framework for Enterprise-Grade LLM Automationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces
  2. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG
  3. 2025MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning
  4. 2025InfoDeepSeek: Benchmarking Agentic Information Seeking for Retrieval-Augmented Generation
  5. 2026GRASP: GRanularity-Aware Search Policy for Agentic RAG
  6. 2025Keyword search is all you need: Achieving RAG-Level Performance without vector databases using agentic tool use
  7. 2024Towards a Search Engine for Machines: Unified Ranking for Multiple Retrieval-Augmented Large Language Models
  8. 2026Agent-Orchestrated Adaptive RAG: A Comparative Study on Structured and Multi-Hop Retrieval