构建多智能体系统，实现足球理解的全面突破
Multi-Agent System for Comprehensive Soccer Understanding
- 设计多智能体协作推理框架，分解复杂足球问题
- 建立包含10,000个问答对的SoccerBench基准，覆盖13项任务
- 首次整合球员、球队等多模态知识库，支持知识驱动推理
近期足球理解研究虽进展迅速，但多集中于孤立任务。为此，本文提出一个综合性框架：(i) 构建首个大规模多模态足球知识库 SoccerWiki，融合球员、球队、裁判、场馆等丰富领域知识，支持知识驱动推理；(ii) 提出最大且最全面的足球专用评测基准 SoccerBench，包含约10,000个跨13类任务的多模态（文本、图像、视频）多选问答对；(iii) 设计 SoccerAgent，一种新型多智能体系统，通过协作推理分解复杂足球问题，利用 SoccerWiki 领域知识实现稳健表现；(iv) 在 SoccerBench 上与代表性 MLLMs 的大量实验对比表明，该代理系统具有显著优势。
原文摘要 · Abstract (English)
Recent advances in 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. Concretely, 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 multimodal (text, image, video) multi-choice QA pairs across 13 distinct tasks; (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 comparisons with representative MLLMs on SoccerBench highlight the superiority of our agentic system.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。