Saved in:
Bibliographic Details
Main Authors: Wu, Tong, Markchom, Thanet
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.03073
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918274131820544
author Wu, Tong
Markchom, Thanet
author_facet Wu, Tong
Markchom, Thanet
contents Visual Question Answering (VQA) for stylised cartoon imagery presents challenges, such as interpreting exaggerated visual abstraction and narrative-driven context, which are not adequately addressed by standard large language models (LLMs) trained on natural images. To investigate this issue, a multi-agent LLM framework is introduced, specifically designed for VQA tasks in cartoon imagery. The proposed architecture consists of three specialised agents: visual agent, language agent and critic agent, which work collaboratively to support structured reasoning by integrating visual cues and narrative context. The framework was systematically evaluated on two cartoon-based VQA datasets: Pororo and Simpsons. Experimental results provide a detailed analysis of how each agent contributes to the final prediction, offering a deeper understanding of LLM-based multi-agent behaviour in cartoon VQA and multimodal inference.
format Preprint
id arxiv_https___arxiv_org_abs_2601_03073
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Understanding Multi-Agent Reasoning with Large Language Models for Cartoon VQA
Wu, Tong
Markchom, Thanet
Computer Vision and Pattern Recognition
Visual Question Answering (VQA) for stylised cartoon imagery presents challenges, such as interpreting exaggerated visual abstraction and narrative-driven context, which are not adequately addressed by standard large language models (LLMs) trained on natural images. To investigate this issue, a multi-agent LLM framework is introduced, specifically designed for VQA tasks in cartoon imagery. The proposed architecture consists of three specialised agents: visual agent, language agent and critic agent, which work collaboratively to support structured reasoning by integrating visual cues and narrative context. The framework was systematically evaluated on two cartoon-based VQA datasets: Pororo and Simpsons. Experimental results provide a detailed analysis of how each agent contributes to the final prediction, offering a deeper understanding of LLM-based multi-agent behaviour in cartoon VQA and multimodal inference.
title Understanding Multi-Agent Reasoning with Large Language Models for Cartoon VQA
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.03073