Lune

ACM MM2025Top-tier venue

Multi-Agent System for Comprehensive Soccer Understanding

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

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 Soc-cerWiki, 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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

4 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark cites Visual Instruction Tuning
  • SpatialScore: Towards Comprehensive Evaluation for Spatial Intelligence cites CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
  • SpatialScore: Towards Comprehensive Evaluation for Spatial Intelligence cites Visual Instruction Tuning
  • SpatialScore: Towards Comprehensive Evaluation for Spatial Intelligence cites Reflexion: language agents with verbal reinforcement learning
  • Visual Instruction Tuning cites Learning Transferable Visual Models From Natural Language Supervision
  • SoccerMaster: A Vision Foundation Model for Soccer Understanding cites Learning Transferable Visual Models From Natural Language Supervision
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers4

  1. SpatialScore: Towards Comprehensive Evaluation for Spatial IntelligenceHaoning Wu, Xiao Huang, Yaohui Chen, Ya Zhang et al.CVPR 2026 · 12 citations
  2. SoccerMaster: A Vision Foundation Model for Soccer UnderstandingHaolin Yang, Jiayuan Rao, Haoning Wu, Weidi XieCVPR 2026 · 10 citations
  3. SciEducator: Scientific Video Understanding and Educating via Deming-Cycle Multi-Agent SystemZhiyu Xu, Weilong Yan, Yufei Shi, Xin Meng et al.CVPR 2026 · 4 citations
  4. Stop Fixating on Prompts: Reasoning Hijacking and Constraint Tightening for Red-Teaming LLM AgentsYanxu Mao, Peipei Liu, Tiehan Cui, Congying Liu et al.ACL 2026

Builds on21

  1. Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
  2. Visual Instruction TuningHaotian Liu, Chunyuan Li, Qingyang Wu, Yong Jae LeeNeurIPS 2023 · 11,349 citations
  3. Reflexion: language agents with verbal reinforcement learningNoah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan et al.NeurIPS 2023 · 5,828 citations
  4. CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model SocietyGuohao Li, Hasan Hammoud, Hani Itani, Dmitrii Khizbullin et al.NeurIPS 2023 · 1,975 citations
  5. MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding BenchmarkXiang Yue, Tianyu Zheng, Yuansheng Ni, Yubo Wang et al.ACL 2025 · 377 citations

Related papers

  1. Towards Universal Soccer Video UnderstandingJiayuan Rao, Haoning Wu, Hao Jiang, Ya Zhang et al.CVPR 2025
  2. SportR: A Benchmark for Multimodal Large Language Model Reasoning in SportsHaotian Xia, Haonan Ge, Junbo Zou, Hyun Woo Choi et al.ICLR 2026 · 17 citations
  3. OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMsCaorui Li, Yu Chen, Yiyan Ji, Jin Xu et al.ICLR 2026 · 53 citations
  4. Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term MemoryLin Long, Yichen He, Wentao Ye, Yiyuan Pan et al.ICLR 2026 · 90 citations
  5. PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World UnderstandingWei Chow, Jiageng Mao, Boyi Li, Daniel Seita et al.ICLR 2025 · 2 citations
Dusk over the sea between two cliffs drawn in fine vertical lines