Multi-Agent System for Comprehensive Soccer Understanding

TL;DR

This paper introduces a comprehensive multi-agent system for holistic soccer understanding, integrating a large knowledge base, a diverse benchmark, and collaborative reasoning to improve performance on complex soccer-related tasks.

Contribution

It presents SoccerWiki, SoccerBench, and SoccerAgent, a novel multi-agent system that advances soccer understanding through knowledge integration, extensive benchmarking, and collaborative reasoning.

Findings

SoccerWiki is the first large-scale multimodal soccer knowledge base.

SoccerBench is the largest soccer-specific benchmark with 10K QA pairs.

SoccerAgent outperforms existing multimodal models on SoccerBench.

Abstract

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.