# SoccerRef-Agents: Multi-Agent System for Automated Soccer Refereeing

arXiv: https://arxiv.org/abs/2604.23392 · HTML: https://mlsanity.com/paper/2604.23392/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 40 references that are in the map.
- First posted on arXiv 25 Apr 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 21 of 21)

- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [Hallucination of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2404.18930/) (2024)
- [FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding](https://mlsanity.com/paper/2004.06704/) (2020)
- [SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos](https://mlsanity.com/paper/1804.04527/) (2018)
- [FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment](https://mlsanity.com/paper/2204.03646/) (2022)
- [Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey](https://mlsanity.com/paper/2411.17558/) (2024)
- [SoccerNet-Caption: Dense Video Captioning for Soccer Broadcasts Commentaries](https://mlsanity.com/paper/2304.04565/) (2023)
- [MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos](https://mlsanity.com/paper/2406.08407/) (2024)
- [Spatio-Temporal Dynamic Inference Network for Group Activity Recognition](https://mlsanity.com/paper/2108.11743/) (2021)
- [Sports-QA: A Large-Scale Video Question Answering Benchmark for Complex and Professional Sports](https://mlsanity.com/paper/2401.01505/) (2024)
- [VARS: Video Assistant Referee System for Automated Soccer Decision Making from Multiple Views](https://mlsanity.com/paper/2304.04617/) (2023)
- [MatchTime: Towards Automatic Soccer Game Commentary Generation](https://mlsanity.com/paper/2406.18530/) (2024)
- [SoccerNet Game State Reconstruction: End-to-End Athlete Tracking and Identification on a Minimap](https://mlsanity.com/paper/2404.11335/) (2024)
- [SPORTU: A Comprehensive Sports Understanding Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2410.08474/) (2024)
- [X-VARS: Introducing Explainability in Football Refereeing with Multi-Modal Large Language Model](https://mlsanity.com/paper/2404.06332/) (2024)
- [Towards Universal Soccer Video Understanding](https://mlsanity.com/paper/2412.01820/) (2024)
- [Multi-Agent System for Comprehensive Soccer Understanding](https://mlsanity.com/paper/2505.03735/) (2025)
- [MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM](https://mlsanity.com/paper/2505.24238/) (2025)
- [TimeSoccer: An End-to-End Multimodal Large Language Model for Soccer Commentary Generation](https://mlsanity.com/paper/2504.17365/) (2025)
- [FenceNet: Fine-grained Footwork Recognition in Fencing](https://mlsanity.com/paper/2204.09434/) (2022)
- [Learning Sparse Temporal Video Mapping for Action Quality Assessment in Floor Gymnastics](https://mlsanity.com/paper/2301.06103/) (2023)

## Abstract (arXiv)

Refereeing is vital in sports, where fair, accurate, and explainable decisions are fundamental. While intelligent assistant technologies are being widely adopted in soccer refereeing, current AI-assisted approaches remain preliminary. Existing research mostly focuses on isolated video perception tasks and lacks the ability to understand and reason about foul scenarios. To fill this gap, we propose SoccerRef-Agents, a holistic and explainable multi-agent decision-making framework for soccer refereeing. The main contributions are: (i) constructing the multimodal benchmark SoccerRefBench with over 1,200 referee theory questions and 600 foul video clips; (ii) building a vector-based knowledge base RefKnowledgeDB using the latest "Laws of the Game" and a classic case database for precise, knowledge-driven reasoning; (iii) designing a novel multi-agent architecture that collaborates via cross-modal RAG to bridge the semantic gap between visual content and regulatory texts. This work explores the technical capability of integrating MLLMs with refereeing expertise, and evaluations show our system significantly outperforms general-purpose MLLMs in decision accuracy and explanation quality. All databases, benchmarks, and code will be made available.