PersonaVlog: Personalized Multimodal Vlog Generation with Multi-Agent Collaboration and Iterative Self-Correction

2025-08-19

AI Summary

Current automated Vlog generation methods rely on predefined scripts, lacking dynamism and personalized expression. To address this, we propose a personalized multimodal Vlog generation framework based on multi-agent collaboration and iterative self-correction. Our approach builds a heterogeneous agent system grounded in multimodal large language models (MLLMs), wherein agents collaboratively perform theme understanding, image-conditioned video generation, background music selection, and inner-monologue speech synthesis. We further introduce a feedback-driven rollback mechanism and ThemeVlogEval—a theme-oriented automatic evaluation framework—to enable dynamic content optimization and personalized alignment. Experiments demonstrate that our method significantly outperforms state-of-the-art approaches across diversity, consistency, and personal expressiveness. It offers practical advantages in efficiency, controllability, and scalability.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Multiagent Learning
• Computer Vision: Multi-modal Vision

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

With the growing demand for short videos and personalized content, automated Video Log (Vlog) generation has become a key direction in multimodal content creation. Existing methods mostly rely on predefined scripts, lacking dynamism and personal expression. Therefore, there is an urgent need for an automated Vlog generation approach that enables effective multimodal collaboration and high personalization. To this end, we propose PersonaVlog, an automated multimodal stylized Vlog generation framework that can produce personalized Vlogs featuring videos, background music, and inner monologue speech based on a given theme and reference image. Specifically, we propose a multi-agent collaboration framework based on Multimodal Large Language Models (MLLMs). This framework efficiently generates high-quality prompts for multimodal content creation based on user input, thereby improving the efficiency and creativity of the process. In addition, we incorporate a feedback and rollback mechanism that leverages MLLMs to evaluate and provide feedback on generated results, thereby enabling iterative self-correction of multimodal content. We also propose ThemeVlogEval, a theme-based automated benchmarking framework that provides standardized metrics and datasets for fair evaluation. Comprehensive experiments demonstrate the significant advantages and potential of our framework over several baselines, highlighting its effectiveness and great potential for generating automated Vlogs.

Problem

• Automated vlog generation lacks personalization and dynamism
• Multimodal content creation needs effective collaboration and high personalization
• Existing methods rely on predefined scripts limiting creative expression

Innovation

• Multi-agent collaboration with MLLMs
• Iterative self-correction via feedback mechanism
• Theme-based automated benchmarking framework