V-agent: An Interactive Video Search System Using Vision-language Models

Abstract

We introduce V-Agent, a novel multi-agent platform designed for advanced video search and interactive user-system conversations. By fine-tuning a vision-language model (VLM) with a small video preference dataset and enhancing it with a retrieval vector from an image-text retrieval model, we overcome the limitations of traditional text-based retrieval systems in multimodal scenarios. The VLM-based retrieval model independently embeds video frames and audio transcriptions from an automatic speech recognition (ASR) module into a shared multimodal representation space, enabling V-Agent to interpret both visual and spoken content for context-aware video search. This system consists of three agents-a routing agent, a search agent, and a chat agent-that work collaboratively to address user intents by refining search outputs and communicating with users. The search agent utilizes the VLM-based retrieval model together with an additional re-ranking module to further enhance video retrieval qual

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keypark2025v

Related papers

• Learning To Retrieve Videos By Asking Questions (2022)8.82
• The VISIONE Video Search System: Exploiting Off-the-shelf Text Search Engines For Large-scale Video Retrieval (2020)10.74
• Llandmark: A Multi-agent Framework For Landmark-aware Multimodal Interactive Video Retrieval (2026)0.00
• Interactive Video Retrieval With Dialog (2019)8.09
• Verve: Versatile Retrieval For Videos Via Unified Embeddings (2026)0.00
• Lazyvlm: Neuro-symbolic Approach To Video Analytics (2025)0.00
• Meta-personalizing Vision-language Models To Find Named Instances In Video (2023)8.60
• Simple Baselines For Interactive Video Retrieval With Questions And Answers (2023)7.16