# Understanding Multi-Agent Reasoning with Large Language Models for Cartoon VQA

arXiv: https://arxiv.org/abs/2601.03073 · HTML: https://mlsanity.com/paper/2601.03073/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 8 of its 27 references that are in the map.
- First posted on arXiv 6 Jan 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 8 of 8)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [VizWiz Grand Challenge: Answering Visual Questions from Blind People](https://mlsanity.com/paper/1802.08218/) (2018)
- [DVQA: Understanding Data Visualizations via Question Answering](https://mlsanity.com/paper/1801.08163/) (2018)
- [DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation](https://mlsanity.com/paper/2412.07589/) (2024)
- [Multi-Agent VQA: Exploring Multi-Agent Foundation Models in Zero-Shot Visual Question Answering](https://mlsanity.com/paper/2403.14783/) (2024)
- [MangaUB: A Manga Understanding Benchmark for Large Multimodal Models](https://mlsanity.com/paper/2407.19034/) (2024)
- [Graph Dual-stream Convolutional Attention Fusion for Precipitation Nowcasting](https://mlsanity.com/paper/2401.07958/) (2024)
- [SimpsonsVQA: Enhancing Inquiry-Based Learning with a Tailored Dataset](https://mlsanity.com/paper/2410.22648/) (2024)

## Abstract (arXiv)

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.