SciEducator：基于戴明循环多智能体系统的科学视频理解与教育
SciEducator: Scientific Video Understanding and Educating via Deming-Cycle Multi-Agent System
将戴明循环（Plan-Do-Study-Act）重构为多智能体自演化推理与反馈机制，用于科学视频的逐步推理与外部知识整合；该迭代式智能体框架可迁移到需要专业领域知识注入的视频问答与教学场景。
原文依据 we propose SciEducator, an iterative self-evolving multi-agent system for scientific video comprehension and education
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期多模态大语言模型（MLLMs）与视频智能体系统的进展显著提升了通用视频理解能力。然而，当应用于科学视频理解与教育这一需要外部专业知识整合与严谨逐步推理的领域时，现有方法往往表现不佳。为弥合这一差距，我们提出 SciEducator，一个用于科学视频理解与教育的迭代式自演化多智能体系统。该设计根植于管理科学中的经典戴明循环，将其 Plan-Do-Study-Act 理念重构为自演化的推理与反馈机制，从而促进对视频中复杂科学活动的解读。此外，SciEducator 能够针对特定科学过程生成多模态教育内容，包括文本说明、视觉引导、音频讲解与交互式参考资料。为支持评测，我们构建了 SciVBench，这是一个包含 500 个经专家验证且有文献依据的科学问答对的基准，覆盖五个类别，涉及物理、化学与日常现象。大量实验表明，SciEducator 在该基准上显著优于领先的闭源 MLLMs（如 Gemini、GPT-4o）与最优的视频智能体，为社区确立了新范式。
英文原文摘要 1387 字符
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, an 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.