Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xu, Zhiyu, Yan, Weilong, Shi, Yufei, Meng, Xin, He, Tao, Zhuang, Huiping, Li, Ming, Fan, Hehe
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2511.17943
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918214901956608
author Xu, Zhiyu
Yan, Weilong
Shi, Yufei
Meng, Xin
He, Tao
Zhuang, Huiping
Li, Ming
Fan, Hehe
author_facet Xu, Zhiyu
Yan, Weilong
Shi, Yufei
Meng, Xin
He, Tao
Zhuang, Huiping
Li, Ming
Fan, Hehe
contents Recent advancements in multimodal large language models (MLLMs) and video agent systems have significantly improved general video understanding. However, when applied to scientific video understanding and educating, a domain that demands external professional knowledge integration and rigorous step-wise reasoning, existing approaches often struggle. To bridge this gap, we propose SciEducator, the first iterative self-evolving multi-agent system for scientific video comprehension and education. Rooted in the classical Deming Cycle from management science, our design reformulates its Plan-Do-Study-Act philosophy into a self-evolving reasoning and feedback mechanism, which facilitates the interpretation of intricate scientific activities in videos. Moreover, SciEducator can produce multimodal educational content tailored to specific scientific processes, including textual instructions, visual guides, audio narrations, and interactive references. To support evaluation, we construct SciVBench, a benchmark consisting of 500 expert-verified and literature-grounded science QA pairs across five categories, covering physical, chemical, and everyday phenomena. Extensive experiments demonstrate that SciEducator substantially outperforms leading closed-source MLLMs (e.g., Gemini, GPT-4o) and state-of-the-art video agents on the benchmark, establishing a new paradigm for the community.
format Preprint
id arxiv_https___arxiv_org_abs_2511_17943
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SciEducator: Scientific Video Understanding and Educating via Deming-Cycle Multi-Agent System
Xu, Zhiyu
Yan, Weilong
Shi, Yufei
Meng, Xin
He, Tao
Zhuang, Huiping
Li, Ming
Fan, Hehe
Computer Vision and Pattern Recognition
Recent advancements in multimodal large language models (MLLMs) and video agent systems have significantly improved general video understanding. However, when applied to scientific video understanding and educating, a domain that demands external professional knowledge integration and rigorous step-wise reasoning, existing approaches often struggle. To bridge this gap, we propose SciEducator, the first iterative self-evolving multi-agent system for scientific video comprehension and education. Rooted in the classical Deming Cycle from management science, our design reformulates its Plan-Do-Study-Act philosophy into a self-evolving reasoning and feedback mechanism, which facilitates the interpretation of intricate scientific activities in videos. Moreover, SciEducator can produce multimodal educational content tailored to specific scientific processes, including textual instructions, visual guides, audio narrations, and interactive references. To support evaluation, we construct SciVBench, a benchmark consisting of 500 expert-verified and literature-grounded science QA pairs across five categories, covering physical, chemical, and everyday phenomena. Extensive experiments demonstrate that SciEducator substantially outperforms leading closed-source MLLMs (e.g., Gemini, GPT-4o) and state-of-the-art video agents on the benchmark, establishing a new paradigm for the community.
title SciEducator: Scientific Video Understanding and Educating via Deming-Cycle Multi-Agent System
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.17943