mPresenter: An Agentic Framework for Generating Multilingual Presentation Videos from Scientific Papers

Generating presentation videos from academic papers is challenging due to the need for longdocument discourse planning and cross-lingual grounding. Existing Paper2Video systems are largely monolingual and often rely on singlepass pipelines, which can limit the coherence and informativeness of the resulting presentations. We present MPRESENTER, a multilingual agentic Paper2Video system that decomposes the task into planning, audience-oriented critique, layout-aware slide generation, and multilingual figure interpretation, enabling iterative refinement at the discourse level. To facilitate reproducible evaluation, we also introduce MPREBENCH, a multilingual benchmark that evaluates presentation videos via question answering as a proxy for effective information transfer. Experimental results indicate that MP-RESENTER improves question-answering accuracy relative to prior systems, while maintaining affordable cost and latency. We release both the system and benchmark to support further research on multilingual Paper2Video 1 . Inputs Reviewer Planner 1. Assets Extraction