arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.03073cs.CV
收藏

通过大型语言模型理解多智能体推理用于漫画视觉问答

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

University of Reading(阅读大学)

Tong Wu, Thanet Markchom

AI总结:

本文提出多智能体LLM框架,用于解决漫画图像中视觉抽象和叙事上下文的VQA问题,通过三个智能体协作提升推理能力。

摘要:

视觉问答(VQA)在风格化漫画图像中面临挑战,例如解释夸张的视觉抽象和叙事驱动的上下文,这不足以通过在自然图像上训练的标准大型语言模型(LLMs)解决。为研究这一问题,引入了一个多智能体LLM框架,专门用于漫画图像的VQA任务。所提出的架构由三个专门的智能体组成:视觉智能体、语言智能体和批评者智能体,它们协同工作,通过整合视觉线索和叙事上下文来支持结构化推理。该框架在两个基于漫画的VQA数据集上进行了系统评估:Pororo和Simpsons。实验结果提供了对每个智能体如何贡献最终预测的详细分析,为LLM基于多智能体行为在漫画VQA和多模态推理中的深入理解提供了新的视角。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑