mlsanityData to 7 Oct 2026

Agentic generative AI for media content discovery at the national football league

arXiv 2510.07297 ↗First posted 8 Oct 2025cs.AIcited by 0

On the map: LLM agents and tool use → Multimodal and embodied agents

Abstract (arXiv)

Generative AI has unlocked new possibilities in content discovery and management. Through collaboration with the National Football League (NFL), we demonstrate how a generative-AI based workflow enables media researchers and analysts to query relevant historical plays using natural language rather than traditional filter-and-click interfaces. The agentic workflow takes a user query as input, breaks it into elements, and translates them into the underlying database query language. Accuracy and latency are further improved through carefully designed semantic caching. The solution achieves over 95 percent accuracy and reduces the average time to find relevant videos from 10 minutes to 30 seconds, significantly increasing the NFL's operational efficiency and allowing users to focus on producing creative content and engaging storylines.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. Builds on 13 of its 24 references that are in the map. First posted on arXiv 8 Oct 2025.

Builds on

13 of 24 references.

References · 13

  1. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 450
  2. 2023Large Language Models for Information Retrieval: A Surveycited by 331
  3. 2023Exploring Chain-of-Thought Style Prompting for Text-to-SQLcited by 69
  4. 2025OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignmentcited by 51
  5. 2024Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigmcited by 31
  6. 2024SPORTU: A Comprehensive Sports Understanding Benchmark for Multimodal Large Language Modelscited by 24
  7. 2024X-VARS: Introducing Explainability in Football Refereeing with Multi-Modal Large Language Modelcited by 22
  8. 2024CoE-SQL: In-Context Learning for Multi-Turn Text-to-SQL with Chain-of-Editionscited by 13
  9. 2024Sportify: Question Answering with Embedded Visualizations and Personified Narratives for Sports Videocited by 8
  10. 2024SCBench: A Sports Commentary Benchmark for Video LLMscited by 7
  11. 2025Domain Adaptation of VLM for Soccer Video Understandingcited by 7
  12. 2024SoccerRAG: Multimodal Soccer Information Retrieval via Natural Queriescited by 6
1 more
  1. 2024Sports Intelligence: Assessing the Sports Understanding Capabilities of Language Models through Question Answering from Text to Videocited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Semantic Action Graph: A Shared Representation for Agent Grounding and Human Interpretation of Sports Highlights
  2. 2025GridMind: A Multi-Agent NLP Framework for Unified, Cross-Modal NFL Data Insights
  3. 2025AgentEval: Generative Agents as Reliable Proxies for Human Evaluation of AI-Generated Content
  4. 2025DIAMOND: An LLM-Driven Agent for Context-Aware Baseball Highlight Summarization
  5. 2026TacticGen: Grounding Adaptable and Scalable Generation of Football Tactics
  6. 2026SVI-Bench: A Dynamic Microworld for Strategic Video Intelligence
  7. 2025Match Chat: Real Time Generative AI and Generative Computing for Tennis
  8. 2025TacEleven: generative tactic discovery for football open play