@inproceedings{kang-etal-2025-diamond,
    title = "{DIAMOND}: An {LLM}-Driven Agent for Context-Aware Baseball Highlight Summarization",
    author = "Kang, Jeonghun  and
      Kwon, Soonmok  and
      Lee, Joonseok  and
      Kim, Byung-Hak",
    editor = "Kamalloo, Ehsan  and
      Gontier, Nicolas  and
      Lu, Xing Han  and
      Dziri, Nouha  and
      Murty, Shikhar  and
      Lacoste, Alexandre",
    booktitle = "Proceedings of the 1st Workshop for Research on Agent Language Models (REALM 2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.realm-1.28/",
    doi = "10.18653/v1/2025.realm-1.28",
    pages = "386--400",
    ISBN = "979-8-89176-264-0",
    abstract = "Highlight summarization in baseball requires balancing statistical analysis with narrative coherence. Traditional approaches{---}such as Win Probability Added (WPA)-based ranking or computer vision-driven event detection{---}can identify scoring plays but often miss strategic depth, momentum shifts, and storyline progression. Manual curation remains the gold standard but is resource-intensive and not scalable.We introduce $\textbf{DIAMOND}$, an $\textbf{LLM-driven agent for context-aware baseball highlight summarization}$ that integrates $\textbf{structured sports analytics with natural language reasoning}$. DIAMOND leverages sabermetric features{---}Win Expectancy, WPA, and Leverage Index{---}to quantify play importance, while an LLM module enhances selection based on contextual narrative value. This hybrid approach ensures both $\textbf{quantitative rigor and qualitative richness}$, surpassing the limitations of purely statistical or vision-based systems.Evaluated on five diverse Korean Baseball Organization League games, DIAMOND improves F1-score from 42.9{\%} (WPA-only) to 84.8{\%}, outperforming both commercial and statistical baselines. Though limited in scale, our results highlight the potential of modular, interpretable agent-based frameworks for event-level summarization in sports and beyond."
}