# Multi-Agent VQA: Exploring Multi-Agent Foundation Models in Zero-Shot Visual Question Answering

Source: [Multi-Agent VQA: Exploring Multi-Agent Foundation Models in Zero-Shot Visual Question Answering](<https://www.sota2.com/research/paper/68fa72a01e209131cea57a24>)

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

Data updated: 2025-10-26T02:30:51.475Z

Authors: Bowen Jiang, Zhijun Zhuang, Shreyas S. Shivakumar, Dan Roth, Camillo J. Taylor

Published: 2024-03-21T18:57:25.000Z

## Abstract

This work explores the zero-shot capabilities of foundation models in Visual Question Answering (VQA) tasks. We propose an adaptive multi-agent system, named Multi-Agent VQA, to overcome the limitations of foundation models in object detection and counting by using specialized agents as tools. Unlike existing approaches, our study focuses on the system's performance without fine-tuning it on specific VQA datasets, making it more practical and robust in the open world. We present preliminary experimental results under zero-shot scenarios and highlight some failure cases, offering new directions for future research.

## 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/2403.14783>)

[PDF](<https://arxiv.org/pdf/2403.14783.pdf>)