Planning Beyond Text: Graph-based Reasoning for Complex Narrative Generation

TL;DR

This paper introduces PLOTTER, a graph-based narrative planning framework that improves coherence and logical consistency in complex story generation by optimizing narrative structures before text synthesis.

Contribution

It proposes a novel graph-based planning approach for narrative generation, outperforming existing methods by focusing on structural graph representations and logical constraints.

Findings

PLOTTER significantly outperforms baseline models in diverse scenarios.

Graph-based planning enhances long-context reasoning in narrative generation.

Optimizing narrative structure before text improves coherence and character development.

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 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.