Multi-Agent System for Comprehensive Soccer Understanding
This work addresses the need for holistic soccer understanding for researchers and practitioners, though it is incremental as it builds on existing multimodal and agent-based methods.
The paper tackles the problem of isolated tasks in soccer understanding by proposing a comprehensive framework, resulting in the creation of a large-scale knowledge base (SoccerWiki), a benchmark with 10K QA pairs (SoccerBench), and a multi-agent system (SoccerAgent) that achieves robust performance.
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.