# Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage

arXiv: https://arxiv.org/abs/2510.02044 · HTML: https://mlsanity.com/paper/2510.02044/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in Conversational and speech RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 27 of its 47 references that are in the map.
- First posted on arXiv 2 Oct 2025.

## Placed in

- Retrieval-augmented generation / [Conversational and speech RAG](https://mlsanity.com/rag/conversational-and-speech-rag/)

## Builds on (most cited first, 27 of 27)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022](https://mlsanity.com/paper/2204.02152/) (2022)
- [Measuring short-form factuality in large language models](https://mlsanity.com/paper/2411.04368/) (2024)
- [Benchmarking Retrieval-Augmented Generation for Medicine](https://mlsanity.com/paper/2402.13178/) (2024)
- [Benchmarking Large Language Models in Retrieval-Augmented Generation](https://mlsanity.com/paper/2309.01431/) (2023)
- [AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head](https://mlsanity.com/paper/2304.12995/) (2023)
- [Kimi-Audio Technical Report](https://mlsanity.com/paper/2504.18425/) (2025)
- [Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming](https://mlsanity.com/paper/2408.16725/) (2024)
- [Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension](https://mlsanity.com/paper/2411.13093/) (2024)
- [Generative Spoken Dialogue Language Modeling](https://mlsanity.com/paper/2203.16502/) (2022)
- [On The Landscape of Spoken Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2504.08528/) (2025)
- [CRAG -- Comprehensive RAG Benchmark](https://mlsanity.com/paper/2406.04744/) (2024)
- [VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks](https://mlsanity.com/paper/2410.19100/) (2024)
- [m&m's: A Benchmark to Evaluate Tool-Use for multi-step multi-modal Tasks](https://mlsanity.com/paper/2403.11085/) (2024)
- [A Survey of Multimodal Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.08748/) (2025)
- [OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning](https://mlsanity.com/paper/2506.00338/) (2025)
- [Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models](https://mlsanity.com/paper/2406.15718/) (2024)
- [Interactive-KBQA: Multi-Turn Interactions for Knowledge Base Question Answering with Large Language Models](https://mlsanity.com/paper/2402.15131/) (2024)
- [WixQA: A Multi-Dataset Benchmark for Enterprise Retrieval-Augmented Generation](https://mlsanity.com/paper/2505.08643/) (2025)
- [OpusLM: A Family of Open Unified Speech Language Models](https://mlsanity.com/paper/2506.17611/) (2025)
- [Enhancing Speech-to-Speech Dialogue Modeling with End-to-End Retrieval-Augmented Generation](https://mlsanity.com/paper/2505.00028/) (2025)
- [Chain-of-Thought Training for Open E2E Spoken Dialogue Systems](https://mlsanity.com/paper/2506.00722/) (2025)
- [AURA: Agent for Understanding, Reasoning, and Automated Tool Use in Voice-Driven Tasks](https://mlsanity.com/paper/2506.23049/) (2025)
- [DailyQA: A Benchmark to Evaluate Web Retrieval Augmented LLMs Based on Capturing Real-World Changes](https://mlsanity.com/paper/2505.17162/) (2025)

## Built on by (most cited first, 15 of 15)

- [SHANKS: Simultaneous Hearing and Thinking for Spoken Language Models](https://mlsanity.com/paper/2510.06917/) (2025)
- [MoshiRAG: Asynchronous Knowledge Retrieval for Full-Duplex Speech Language Models](https://mlsanity.com/paper/2604.12928/) (2026)
- [NOVA: NOise-aware Verbal Confidence CAlibration for Robust Large Language Models in RAG Systems](https://mlsanity.com/paper/2601.11004/) (2026)
- [Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions](https://mlsanity.com/paper/2602.05220/) (2026)
- [From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models](https://mlsanity.com/paper/2603.04592/) (2026)
- [Thinking While Speaking: Inference-Time Knowledge Transfer for Responsive and Intelligent Conversational Voice Agents](https://mlsanity.com/paper/2511.07397/) (2025)
- [Speculative Interaction Agents: Building Real-Time Agents with Asynchronous I/O and Speculative Tool Calling](https://mlsanity.com/paper/2605.13360/) (2026)
- [TiCo: Time-Controllable Spoken Dialogue Model](https://mlsanity.com/paper/2603.22267/) (2026)
- [RADAR: Defending RAG Dynamically against Retrieval Corruption](https://mlsanity.com/paper/2605.22041/) (2026)
- [Back to Basics: Revisiting ASR in the Age of Voice Agents](https://mlsanity.com/paper/2603.25727/) (2026)
- [ProactiveLLM: Learning Active Interaction for Streaming Large Language Models](https://mlsanity.com/paper/2606.00523/) (2026)
- [When Does Streaming Tool Use Help? Characterizing Tool-Intent Stabilization in Streaming Retrieval-Augmented Generation](https://mlsanity.com/paper/2606.20113/) (2026)
- [Context Spanning: A Communication Framework for Full-Duplex Speech Models and External LLM Backends](https://mlsanity.com/paper/2609.33443/) (2026)
- [RUBATO: Decoupled Clocks Allow Full-Duplex Models to Think as Fast as They Can](https://mlsanity.com/paper/2610.14299/) (2026)
- [RASSG: Repair-Aware Semantic Survival Gating for Streaming Tool Execution](https://mlsanity.com/paper/2610.14659/) (2026)

## Abstract (arXiv)

End-to-end speech-in speech-out dialogue systems are emerging as a powerful alternative to traditional ASR-LLM-TTS pipelines, generating more natural, expressive responses with significantly lower latency. However, these systems remain prone to hallucinations due to limited factual grounding. While text-based dialogue systems address this challenge by integrating tools such as web search and knowledge graph APIs, we introduce the first approach to extend tool use directly into speech-in speech-out systems. A key challenge is that tool integration substantially increases response latency, disrupting conversational flow. To mitigate this, we propose Streaming Retrieval-Augmented Generation (Streaming RAG), a novel framework that reduces user-perceived latency by predicting tool queries in parallel with user speech, even before the user finishes speaking. Specifically, we develop a post-training pipeline that teaches the model when to issue tool calls during ongoing speech and how to generate spoken summaries that fuse audio queries with retrieved text results, thereby improving both accuracy and responsiveness. To evaluate our approach, we construct AudioCRAG, a benchmark created by converting queries from the publicly available CRAG dataset into speech form. Experimental results demonstrate that our streaming RAG approach increases QA accuracy by up to 200% relative (from 11.1% to 34.2% absolute) and further enhances user experience by reducing tool use latency by 20%. Importantly, our streaming RAG approach is modality-agnostic and can be applied equally to typed input, paving the way for more agentic, real-time AI assistants.