Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.21253 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913056661962752 |
|---|---|
| author | Gu, Hanwen Guo, Chao Wang, Junle Xie, Wenda Lv, Yisheng |
| author_facet | Gu, Hanwen Guo, Chao Wang, Junle Xie, Wenda Lv, Yisheng |
| contents | 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 the direct sequential text representations used 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 planning narratives on structural graph representations-rather than directly on text-is crucial to enhance the long context reasoning of LLMs in complex narrative generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_21253 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Planning Beyond Text: Graph-based Reasoning for Complex Narrative Generation Gu, Hanwen Guo, Chao Wang, Junle Xie, Wenda Lv, Yisheng Computation and Language Artificial Intelligence 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 the direct sequential text representations used 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 planning narratives on structural graph representations-rather than directly on text-is crucial to enhance the long context reasoning of LLMs in complex narrative generation. |
| title | Planning Beyond Text: Graph-based Reasoning for Complex Narrative Generation |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2604.21253 |