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

2026-04-22

AI Summary

This work addresses the challenge that large language models struggle to maintain global coherence, logical consistency, and smooth character development in complex narrative generation. To this end, the authors propose PLOTTER, a novel framework that introduces structured graph-based reasoning into the narrative planning phase. PLOTTER explicitly controls narrative structure by constructing event and character graphs and iteratively executing an evaluation–planning–revision loop over them. This approach integrates causal modeling, graph optimization under logical constraints, and synergistic reasoning between large language models and graph structures. Experimental results demonstrate that PLOTTER significantly outperforms existing baselines across diverse narrative scenarios, underscoring the critical role of graph-based planning in enhancing the quality of long-context storytelling.

Technology Category

• Natural Language Processing: Generation
• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• narrative coherence
• logical consistency
• character development
• structural fractures
• complex narrative generation

Innovation

• graph-based reasoning
• narrative planning
• event graph
• character graph
• logical constraints