# VDMA: Video Question Answering with Dynamically Generated Multi-Agents

Source: [VDMA: Video Question Answering with Dynamically Generated Multi-Agents](<https://www.sota2.com/research/paper/68fa74071e209131cea5f592>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:07.853Z

Authors: Noriyuki Kugo, Tatsuya Ishibashi, Kosuke Ono, Yuji Sato

Published: 2024-07-04T03:40:36.000Z

## Abstract

This technical report provides a detailed description of our approach to the EgoSchema Challenge 2024. The EgoSchema Challenge aims to identify the most appropriate responses to questions regarding a given video clip. In this paper, we propose Video Question Answering with Dynamically Generated Multi-Agents (VDMA). This method is a complementary approach to existing response generation systems by employing a multi-agent system with dynamically generated expert agents. This method aims to provide the most accurate and contextually appropriate responses. This report details the stages of our approach, the tools employed, and the results of our experiments.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2407.03610>)

[PDF](<https://arxiv.org/pdf/2407.03610.pdf>)