TacticGen: Grounding Adaptable and Scalable Generation of Football Tactics

2026-04-20

AI Summary

Existing approaches to football tactic generation suffer from limited scalability and adaptability, often restricted to trajectory prediction. This work proposes a multi-agent diffusion Transformer framework that models tactics as sequences of coordinated agent movements and interactions conditioned on match context. It presents the first diffusion-based method capable of adaptive tactic generation, allowing flexible specification of objectives via rules, natural language, or neural models. The architecture integrates agent self-attention with context-aware cross-attention mechanisms and employs classifier guidance to enhance generation quality. Trained on over 3.3 million events and 100 million tracking frames, the model achieves state-of-the-art accuracy in trajectory prediction, while expert evaluations confirm that the generated tactics exhibit both realism and strategic value.

Technology Category

• Multiagent Systems: Adversarial Agents
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Natural Language Processing: Generation

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Success in association football relies on both individual skill and coordinated tactics. While recent advancements in spatio-temporal data and deep learning have enabled predictive analyses like trajectory forecasting, the development of tactical design remains limited. Bridging this gap is essential, as prediction reveals what is likely to occur, whereas tactic generation determines what should occur to achieve strategic objectives. In this work, we present TacticGen, a generative model for adaptable and scalable tactic generation. TacticGen formulates tactics as sequences of multi-agent movements and interactions conditioned on the game context. It employs a multi-agent diffusion transformer with agent-wise self-attention and context-aware cross-attention to capture cooperative and competitive dynamics among players and the ball. Trained with over 3.3 million events and 100 million tracking frames from top-tier leagues, TacticGen achieves state-of-the-art precision in predicting player trajectories. Building on it, TacticGen enables adaptable tactic generation tailored to diverse inference-time objectives through classifier guidance mechanism, specified via rules, natural language, or neural models. Its modeling performance is also inherently scalable. A case study with football experts confirms that TacticGen generates realistic, strategically valuable tactics, demonstrating its practical utility for tactical planning in professional football. The project page is available at: https://shengxu.net/TacticGen/.

Problem

• tactic generation
• football tactics
• spatio-temporal data
• multi-agent coordination
• strategic planning

Innovation

• multi-agent diffusion transformer
• tactic generation
• context-aware cross-attention
• classifier guidance
• spatio-temporal modeling