Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yan, Haiyang, Zhou, Hongyun, Xu, Peng, Feng, Xiaoxue, Liu, Mengyi
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2603.17307
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917351277985792
author Yan, Haiyang
Zhou, Hongyun
Xu, Peng
Feng, Xiaoxue
Liu, Mengyi
author_facet Yan, Haiyang
Zhou, Hongyun
Xu, Peng
Feng, Xiaoxue
Liu, Mengyi
contents Despite rapid developments and widespread applications of MLLM agents, they still struggle with long-form video understanding (LVU) tasks, which are characterized by high information density and extended temporal spans. Recent research on LVU agents demonstrates that simple task decomposition and collaboration mechanisms are insufficient for long-chain reasoning tasks. Moreover, directly reducing the time context through embedding-based retrieval may lose key information of complex problems. In this paper, we propose Symphony, a multi-agent system, to alleviate these limitations. By emulating human cognition patterns, Symphony decomposes LVU into fine-grained subtasks and incorporates a deep reasoning collaboration mechanism enhanced by reflection, effectively improving the reasoning capability. Additionally, Symphony provides a VLM-based grounding approach to analyze LVU tasks and assess the relevance of video segments, which significantly enhances the ability to locate complex problems with implicit intentions and large temporal spans. Experimental results show that Symphony achieves state-of-the-art performance on LVBench, LongVideoBench, VideoMME, and MLVU, with a 5.0% improvement over the prior state-of-the-art method on LVBench. Code is available at https://github.com/Haiyang0226/Symphony.
format Preprint
id arxiv_https___arxiv_org_abs_2603_17307
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Symphony: A Cognitively-Inspired Multi-Agent System for Long-Video Understanding
Yan, Haiyang
Zhou, Hongyun
Xu, Peng
Feng, Xiaoxue
Liu, Mengyi
Computer Vision and Pattern Recognition
Artificial Intelligence
Despite rapid developments and widespread applications of MLLM agents, they still struggle with long-form video understanding (LVU) tasks, which are characterized by high information density and extended temporal spans. Recent research on LVU agents demonstrates that simple task decomposition and collaboration mechanisms are insufficient for long-chain reasoning tasks. Moreover, directly reducing the time context through embedding-based retrieval may lose key information of complex problems. In this paper, we propose Symphony, a multi-agent system, to alleviate these limitations. By emulating human cognition patterns, Symphony decomposes LVU into fine-grained subtasks and incorporates a deep reasoning collaboration mechanism enhanced by reflection, effectively improving the reasoning capability. Additionally, Symphony provides a VLM-based grounding approach to analyze LVU tasks and assess the relevance of video segments, which significantly enhances the ability to locate complex problems with implicit intentions and large temporal spans. Experimental results show that Symphony achieves state-of-the-art performance on LVBench, LongVideoBench, VideoMME, and MLVU, with a 5.0% improvement over the prior state-of-the-art method on LVBench. Code is available at https://github.com/Haiyang0226/Symphony.
title Symphony: A Cognitively-Inspired Multi-Agent System for Long-Video Understanding
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2603.17307