# PhoStream: Benchmarking Real-World Streaming for Omnimodal Assistants in Mobile Scenarios

arXiv: https://arxiv.org/abs/2601.22575 · HTML: https://mlsanity.com/paper/2601.22575/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Video understanding with MLLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 30 of its 37 references that are in the map.
- First posted on arXiv 30 Jan 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Video understanding with MLLMs](https://mlsanity.com/mllm/video-understanding-with-mllms/)

## Builds on (most cited first, 30 of 30)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?](https://mlsanity.com/paper/2403.14624/) (2024)
- [DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding](https://mlsanity.com/paper/2412.10302/) (2024)
- [ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering](https://mlsanity.com/paper/1906.02467/) (2019)
- [Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset](https://mlsanity.com/paper/2402.14804/) (2024)
- [AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents](https://mlsanity.com/paper/2405.14573/) (2024)
- [Seed-TTS: A Family of High-Quality Versatile Speech Generation Models](https://mlsanity.com/paper/2406.02430/) (2024)
- [VideoLLM-online: Online Video Large Language Model for Streaming Video](https://mlsanity.com/paper/2406.11816/) (2024)
- [Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence](https://mlsanity.com/paper/2505.23747/) (2025)
- [WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition](https://mlsanity.com/paper/2110.03370/) (2021)
- [Mobile-Agent-v3: Fundamental Agents for GUI Automation](https://mlsanity.com/paper/2508.15144/) (2025)
- [MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe](https://mlsanity.com/paper/2509.18154/) (2025)
- [StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding](https://mlsanity.com/paper/2411.03628/) (2024)
- [OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?](https://mlsanity.com/paper/2501.05510/) (2025)
- [Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction](https://mlsanity.com/paper/2501.03218/) (2025)
- [AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents](https://mlsanity.com/paper/2407.17490/) (2024)
- [StreamingVLM: Real-Time Understanding for Infinite Video Streams](https://mlsanity.com/paper/2510.09608/) (2025)
- [OpenELM: An Efficient Language Model Family with Open Training and Inference Framework](https://mlsanity.com/paper/2404.14619/) (2024)
- [AlignBench: Benchmarking Chinese Alignment of Large Language Models](https://mlsanity.com/paper/2311.18743/) (2023)
- [OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts](https://mlsanity.com/paper/2503.22952/) (2025)
- [ProactiveVideoQA: A Comprehensive Benchmark Evaluating Proactive Interactions in Video Large Language Models](https://mlsanity.com/paper/2507.09313/) (2025)
- [BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices](https://mlsanity.com/paper/2411.10640/) (2024)
- [MMDuet2: Enhancing Proactive Interaction of Video MLLMs with Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2512.06810/) (2025)
- [EgoBlind: Towards Egocentric Visual Assistance for the Blind](https://mlsanity.com/paper/2503.08221/) (2025)
- [SmartBench: Is Your LLM Truly a Good Chinese Smartphone Assistant?](https://mlsanity.com/paper/2503.06029/) (2025)

## Built on by (most cited first, 10 of 10)

- [A Simple Baseline for Streaming Video Understanding](https://mlsanity.com/paper/2604.02317/) (2026)
- [OmniGAIA: Towards Native Omni-Modal AI Agents](https://mlsanity.com/paper/2602.22897/) (2026)
- [What Should a Streaming Video Model Remember?](https://mlsanity.com/paper/2606.16353/) (2026)
- [StreamTTT: Reconciling Real-Time Perception and Long-Term Memory in Streaming VLMs](https://mlsanity.com/paper/2608.13416/) (2026)
- [Harnessing Streaming Video in the Wild](https://mlsanity.com/paper/2606.08615/) (2026)
- [Omni-DuplexEval: Evaluating Real-time Duplex Omni-modal Interaction](https://mlsanity.com/paper/2605.17360/) (2026)
- [GuideMe: Multi-Domain Task Guidance and Intervention in Streaming Video](https://mlsanity.com/paper/2607.02991/) (2026)
- [X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding](https://mlsanity.com/paper/2606.02482/) (2026)
- [Video-IFBench: Evaluating Instruction Following of Multimodal LLMs in Video Understanding Scenarios](https://mlsanity.com/paper/2608.25529/) (2026)
- [APM-Bench: Benchmarking Cross-session Persistent Memory for Egocentric Streaming Video Assistants](https://mlsanity.com/paper/2609.37559/) (2026)

## Abstract (arXiv)

Multimodal Large Language Models excel at offline audio-visual understanding, but their ability to serve as mobile assistants in continuous real-world streams remains underexplored. In daily phone use, mobile assistants must track streaming audio-visual inputs and respond at the right time, yet existing benchmarks are often restricted to multiple-choice questions or use shorter videos. In this paper, we introduce PhoStream, the first mobile-centric streaming benchmark that unifies on-screen and off-screen scenarios to evaluate video, audio, and temporal reasoning. PhoStream contains 5,572 open-ended QA pairs from 578 videos across 4 scenarios and 10 capabilities. We build it with an Automated Generative Pipeline backed by rigorous human verification, and evaluate models using a realistic Online Inference Pipeline and LLM-as-a-Judge evaluation for open-ended responses. Experiments reveal a temporal asymmetry in LLM-judged scores (0-100): models perform well on Instant and Backward tasks (Gemini 3 Pro exceeds 80), but drop sharply on Forward tasks (16.40), largely due to early responses before the required visual and audio cues appear. This highlights a fundamental limitation: current MLLMs struggle to decide when to speak, not just what to say. Code and datasets used in this work will be made publicly accessible at https://github.com/Lucky-Lance/PhoStream.