Saved in:
Bibliographic Details
Main Authors: Yan, Weicai, Dai, Yuhong, Ran, Qi, Li, Haodong, Lin, Wang, Jin, Tao, Xie, Xing, Liao, Hao, Lian, Jianxun
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.03447
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916042053255168
author Yan, Weicai
Dai, Yuhong
Ran, Qi
Li, Haodong
Lin, Wang
Jin, Tao
Xie, Xing
Liao, Hao
Lian, Jianxun
author_facet Yan, Weicai
Dai, Yuhong
Ran, Qi
Li, Haodong
Lin, Wang
Jin, Tao
Xie, Xing
Liao, Hao
Lian, Jianxun
contents Proactive and real-time interactive experiences are essential for human-like AI companions, yet face three key challenges: (1) achieving low-latency inference under continuous streaming inputs, (2) autonomously deciding when to respond, and (3) controlling both quality and quantity of generated content to meet real-time constraints. In this work, we instantiate AI companions through two gaming scenarios, commentator and guide, selected for their suitability for automatic evaluation. We introduce the Live Gaming Benchmark, a large-scale dataset with three representative scenarios: solo commentary, co-commentary, and user guidance, and present Proact-VL, a general framework that shapes multimodal language models into proactive, real-time interactive agents capable of human-like environment perception and interaction. Extensive experiments show Proact-VL achieves superior response latency and quality while maintaining strong video understanding capabilities, demonstrating its practicality for real-time interactive applications.
format Preprint
id arxiv_https___arxiv_org_abs_2603_03447
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Proact-VL: A Proactive VideoLLM for Real-Time AI Companions
Yan, Weicai
Dai, Yuhong
Ran, Qi
Li, Haodong
Lin, Wang
Jin, Tao
Xie, Xing
Liao, Hao
Lian, Jianxun
Computer Vision and Pattern Recognition
Proactive and real-time interactive experiences are essential for human-like AI companions, yet face three key challenges: (1) achieving low-latency inference under continuous streaming inputs, (2) autonomously deciding when to respond, and (3) controlling both quality and quantity of generated content to meet real-time constraints. In this work, we instantiate AI companions through two gaming scenarios, commentator and guide, selected for their suitability for automatic evaluation. We introduce the Live Gaming Benchmark, a large-scale dataset with three representative scenarios: solo commentary, co-commentary, and user guidance, and present Proact-VL, a general framework that shapes multimodal language models into proactive, real-time interactive agents capable of human-like environment perception and interaction. Extensive experiments show Proact-VL achieves superior response latency and quality while maintaining strong video understanding capabilities, demonstrating its practicality for real-time interactive applications.
title Proact-VL: A Proactive VideoLLM for Real-Time AI Companions
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.03447