PresentAgent-2: Towards Generalist Multimodal Presentation Agents

• URL: http://arxiv.org/abs/2605.11363v1
• Date: Tue, 12 May 2026 00:32:24 GMT
• Title: PresentAgent-2: Towards Generalist Multimodal Presentation Agents
• Abstract summary: PresentAgent-2 is an agentic framework for generating presentation videos from user queries.<n>Given an open-ended user query and a selected presentation mode, PresentAgent-2 first summarizes the query into a focused topic.<n>It then constructs presentation slides, generates mode-specific scripts, and composes slides, audio, and dynamic media into a complete presentation video.
• Score: 19.677257938855416
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Presentation generation is moving beyond static slide creation toward end-to-end presentation video generation with research grounding, multimodal media, and interactive delivery. We introduce PresentAgent-2, an agentic framework for generating presentation videos from user queries. Given an open-ended user query and a selected presentation mode, PresentAgent-2 first summarizes the query into a focused topic and performs deep research over presentation-friendly sources to collect multimodal resources, including relevant text, images, GIFs, and videos. It then constructs presentation slides, generates mode-specific scripts, and composes slides, audio, and dynamic media into a complete presentation video. PresentAgent-2 supports three independent presentation modes within a unified framework: Single Presentation, which generates a single-speaker narrated presentation video; Discussion, which creates a multi-speaker presentation with structured speaker roles, such as for asking guiding questions, explaining concepts, clarifying details, and summarizing key points; and Interaction, which independently supports answering audience questions grounded in the generated slides, scripts, retrieved evidence, and presentation context. To evaluate these capabilities, we build a multimodal presentation benchmark covering single presentation, discussion, and interaction scenarios, with task-specific evaluation criteria for content quality, media relevance, dynamic media use, dialogue naturalness, and interaction grounding. Overall, PresentAgent-2 extends presentation generation from document-dependent slide creation to query-driven, research-grounded presentation video generation with multimodal media, dialogue, and interaction. Code: https://github.com/AIGeeksGroup/PresentAgent-2. Website: https://aigeeksgroup.github.io/PresentAgent-2.

Related papers

• AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding [73.05946667683259]
  Recent large language models (MLLMs) show strong perception but struggle in multi-speaker, dialogue-centric settings.<n>We introduce AMUSE, a benchmark designed around tasks that are inherently agentic.<n>We propose RAFT, a data-efficient agentic alignment framework that integrates reward optimization with intrinsic multimodal self-evaluation.
  arXiv  Detail & Related papers  (2025-12-18T07:01:47Z)
• PresentCoach: Dual-Agent Presentation Coaching through Exemplars and Interactive Feedback [36.12055243344036]
  We introduce a dual-agent system that supports presentation practice through two complementary roles: the Ideal Presentation Agent and the Coach Agent.<n>The Ideal Presentation Agent converts user-provided slides into model presentation videos by combining slide processing, visual-language analysis, narration script generation, personalized voice synthesis, and synchronized video assembly.<n>The Coach Agent then evaluates user-recorded presentations against these exemplars, conducting multimodal speech analysis and delivering structured feedback in an Observation-Impact-Suggestion (OIS) format.
  arXiv  Detail & Related papers  (2025-11-19T09:15:21Z)
• Paper2Video: Automatic Video Generation from Scientific Papers [62.634562246594555]
  Paper2Video is the first benchmark of 101 research papers paired with author-created presentation videos, slides, and speaker metadata.<n>We propose PaperTalker, the first multi-agent framework for academic presentation video generation.
  arXiv  Detail & Related papers  (2025-10-06T17:58:02Z)
• PresentAgent: Multimodal Agent for Presentation Video Generation [30.274831875701217]
  We present PresentAgent, a multimodal agent that transforms long-form documents into narrated presentation videos.<n>To achieve this integration, PresentAgent employs a modular pipeline that segments the input document, plans and renders slide-style visual frames.<n>Given the complexity of evaluating such multimodal outputs, we introduce PresentEval, a unified assessment framework powered by Vision-Language Models.
  arXiv  Detail & Related papers  (2025-07-05T13:24:15Z)
• PreGenie: An Agentic Framework for High-quality Visual Presentation Generation [44.93958820783717]
  PreGenie is an agentic and modular framework powered by multimodal large language models (MLLMs) for generating high-quality visual presentations.<n>It operates in two stages: (1) Analysis and Initial Generation, which summarizes multimodal input and generates initial code, and (2) Review and Re-generation, which iteratively reviews intermediate code and rendered slides to produce final, high-quality presentations.
  arXiv  Detail & Related papers  (2025-05-27T18:36:19Z)
• Multimodal Lecture Presentations Dataset: Understanding Multimodality in Educational Slides [57.86931911522967]
  We test the capabilities of machine learning models in multimodal understanding of educational content. Our dataset contains aligned slides and spoken language, for 180+ hours of video and 9000+ slides, with 10 lecturers from various subjects. We introduce PolyViLT, a multimodal transformer trained with a multi-instance learning loss that is more effective than current approaches.
  arXiv  Detail & Related papers  (2022-08-17T05:30:18Z)
• VMSMO: Learning to Generate Multimodal Summary for Video-based News Articles [63.32111010686954]
  We propose the task of Video-based Multimodal Summarization with Multimodal Output (VMSMO) The main challenge in this task is to jointly model the temporal dependency of video with semantic meaning of article. We propose a Dual-Interaction-based Multimodal Summarizer (DIMS), consisting of a dual interaction module and multimodal generator.
  arXiv  Detail & Related papers  (2020-10-12T02:19:16Z)
• Dynamic Graph Representation Learning for Video Dialog via Multi-Modal Shuffled Transformers [89.00926092864368]
  We present a semantics-controlled multi-modal shuffled Transformer reasoning framework for the audio-visual scene aware dialog task. We also present a novel dynamic scene graph representation learning pipeline that consists of an intra-frame reasoning layer producing-semantic graph representations for every frame. Our results demonstrate state-of-the-art performances on all evaluation metrics.
  arXiv  Detail & Related papers  (2020-07-08T02:00:22Z)
• Video-Grounded Dialogues with Pretrained Generation Language Models [88.15419265622748]
  We leverage the power of pre-trained language models for improving video-grounded dialogue. We propose a framework by formulating sequence-to-grounded dialogue tasks as a sequence-to-grounded task. Our framework allows fine-tuning language models to capture dependencies across multiple modalities.
  arXiv  Detail & Related papers  (2020-06-27T08:24:26Z)
• Interview: A Large-Scale Open-Source Corpus of Media Dialog [11.28504775964698]
  We introduce 'Interview': a large-scale (105K conversations) media dialog dataset collected from news interview transcripts. Compared to existing large-scale proxies for conversational data, language models trained on our dataset exhibit better zero-shot out-of-domain performance. 'Interview' contains speaker role annotations for each turn, facilitating the development of engaging, responsive dialog systems.
  arXiv  Detail & Related papers  (2020-04-07T02:44:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.