全方位足球理解之多智能體系統

Multi-Agent System for Comprehensive Soccer Understanding

May 6, 2025

作者: Jiayuan Rao, Zifeng Li, Haoning Wu, Ya Zhang, Yanfeng Wang, Weidi Xie

cs.AI

摘要

近期，AI驱动的足球理解领域取得了快速进展，然而现有研究主要集中于孤立或狭窄的任务。为填补这一空白，我们提出了一个全面的框架，以实现对足球的整体理解。具体而言，本文做出了以下贡献：(i) 我们构建了SoccerWiki，这是首个大规模多模态足球知识库，整合了关于球员、球队、裁判和场地的丰富领域知识，以支持知识驱动的推理；(ii) 我们推出了SoccerBench，这是最大且最全面的足球专用基准测试，包含约10K标准化多模态（文本、图像、视频）多选题问答对，涵盖13个不同的理解任务，通过自动化流程和人工验证精心筛选；(iii) 我们引入了SoccerAgent，一种新颖的多智能体系统，通过协作推理分解复杂的足球问题，利用SoccerWiki的领域专业知识，并实现了稳健的性能；(iv) 广泛的评估和消融实验，在SoccerBench上对最先进的多模态大语言模型（MLLMs）进行基准测试，凸显了我们提出的智能体系统的优越性。所有数据和代码均已公开，访问地址为：https://jyrao.github.io/SoccerAgent/。

English

Recent advancements in AI-driven soccer understanding have demonstrated rapid progress, yet existing research predominantly focuses on isolated or narrow tasks. To bridge this gap, we propose a comprehensive framework for holistic soccer understanding. Specifically, we make the following contributions in this paper: (i) we construct SoccerWiki, the first large-scale multimodal soccer knowledge base, integrating rich domain knowledge about players, teams, referees, and venues to enable knowledge-driven reasoning; (ii) we present SoccerBench, the largest and most comprehensive soccer-specific benchmark, featuring around 10K standardized multimodal (text, image, video) multi-choice QA pairs across 13 distinct understanding tasks, curated through automated pipelines and manual verification; (iii) we introduce SoccerAgent, a novel multi-agent system that decomposes complex soccer questions via collaborative reasoning, leveraging domain expertise from SoccerWiki and achieving robust performance; (iv) extensive evaluations and ablations that benchmark state-of-the-art MLLMs on SoccerBench, highlighting the superiority of our proposed agentic system. All data and code are publicly available at: https://jyrao.github.io/SoccerAgent/.