CogenPVG：用于说服性视频生成的认知增强反思式多智能体框架
CogenPVG: Cognitive-Enhanced Reflective Multi-Agent Framework for Persuasive Video Generation
浏览论文内容
中文总结 AI 辅助
提出CogenPVG认知增强反思式多智能体框架，通过四阶段流程与ELM理论指导，实现高说服力视频的自动化生成，实验证明其性能最优。
中文摘要 AI 辅助
说服性视频生成（PVG）是一个有价值但尚未充分探索的研究课题。尽管多模态内容生成取得了显著进展，但由人工智能赋能、自动化生成具有较强说服力且类似人工制作的视频仍然是一项艰巨的挑战。在本文中，我们提出了CogenPVG，一种针对说服性视频生成任务量身定制的新型认知增强反思式多智能体框架。根据用户给出的主题和立场，我们将复杂的生成过程解耦为四个顺序阶段：论点推理、分镜规划、素材创建和后期编辑，模仿人类视频制作人的工作流程。为确保高说服力，每个阶段配备一对生成器和评论家智能体，遵循基于扎实的说服心理学理论——精细加工可能性模型（ELM）的反思性细化方案。在论点推理阶段，我们在批判性思维理论的指导下生成高度逻辑性和可信的推理思路，通过ELM的中心路径实现认知增强。对于其他三个阶段，我们生成并优化多模态素材，在启发式理论的指导下将其组装成说服性视频，作为ELM的外围路径。据我们所知，CogenPVG是首个专注于一般说服性主题、不局限于商业目的的工作。大量实验和全面分析表明，我们的框架实现了最佳的说服性能，从而证明了我们提出的用于PVG任务的多智能体框架的有效性。
英文摘要
Persuasive video generation (PVG) is a valuable yet under-explored research topic. Despite the significant advances in multimodal content generation, AI-empowered automated creation of human-made-like videos with substantial persuasiveness remains a formidable challenge. In this paper, we propose CogenPVG, a novel Cognitive-Enhanced reflective multi-agent framework tailored for Persuasive Video Generation task. Given the topic and stance from the user, we decouple the sophisticated generation process into four sequential stages: argument reasoning, storyboard planning, asset creation, and post-editing, imitating the workflow of human video producers. To ensure high persuasiveness, each stage is equipped with a pair of generator and critic agents, following a reflective refinement scheme grounded in a solid psychological theory of persuasion, the Elaboration Likelihood Model (ELM). In the argument reasoning stage, we generate highly logical and credible reasoning thoughts under the guidance of critical thinking theory, enabling cognitive enhancement via the central route of the ELM. For the other three stages, we generate and optimize multimodal assets, assembling them into a persuasive video guided by theories of heuristics, as the peripheral route of the ELM. To the best of our knowledge, CogenPVG is the first work focused on general persuasive topics, without being confined to commercial purposes. Extensive experiments and comprehensive analysis demonstrate that our framework achieves the best persuasion performance, thereby proving the effectiveness of our proposed multi-agent framework for the PVG task.
发表机构
- Beihang University（北京航空航天大学）
- Zhongguancun Laboratory（中关村实验室）
- Beijing Information Science and Technology University（北京信息科技大学）
- Beijing Technology and Business University（北京工商大学）
机构由 AI 辅助整理，请以论文原文为准。
