VideoAgent: Personalized Synthesis of Scientific Videos
This addresses the problem of effective knowledge dissemination for researchers and educators by providing a tool for personalized dynamic video creation, representing a novel application rather than an incremental improvement in existing methods.
The paper tackles the challenge of automating personalized scientific video generation by introducing VideoAgent, a multi-agent framework that synthesizes videos from research papers, achieving performance comparable to human-level quality and outperforming existing commercial services.
Automating the generation of scientific videos is a crucial yet challenging task for effective knowledge dissemination. However, existing works on document automation primarily focus on static media such as posters and slides, lacking mechanisms for personalized dynamic orchestration and multimodal content synchronization. To address these challenges, we introduce VideoAgent, a novel multi-agent framework that synthesizes personalized scientific videos through a conversational interface. VideoAgent parses a source paper into a fine-grained asset library and, guided by user requirements, orchestrates a narrative flow that synthesizes both static slides and dynamic animations to explain complex concepts. To enable rigorous evaluation, we also propose SciVidEval, the first comprehensive suite for this task, which combines automated metrics for multimodal content quality and synchronization with a Video-Quiz-based human evaluation to measure knowledge transfer. Extensive experiments demonstrate that our method significantly outperforms existing commercial scientific video generation services and approaches human-level quality in scientific communication.