@inproceedings{gu-etal-2026-planning,
    title = "Planning Beyond Text: Graph-based Reasoning for Complex Narrative Generation",
    author = "Gu, Hanwen  and
      Guo, Chao  and
      Wang, Junle  and
      Xie, Wenda  and
      Lv, Yisheng",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1874/",
    pages = "37579--37610",
    ISBN = "979-8-89176-395-1",
    abstract = "While LLMs demonstrate remarkable fluency in narrative generation, existing methods struggle to maintain global narrative coherence, contextual logical consistency, and smooth character development, often producing monotonous scripts with structural fractures. To this end, we introduce PLOTTER, a framework that performs narrative planning on structural graph representations instead of direct sequential text representations in existing work. Specifically, PLOTTER executes the Evaluate-Plan-Revise cycle on the event graph and character graph. By diagnosing and repairing issues of the graph topology under rigorous logical constraints, the model optimizes the causality and narrative skeleton before complete context generation. Experiments demonstrate that PLOTTER significantly outperforms representative baselines across diverse narrative scenarios. These findings verify that manipulating narrative planning on structural graph representations{---}rather than direct text representations{---}is crucial to enhance the long-context reasoning of LLMs in complex narrative generation."
}