Long Story Generation via Knowledge Graph and Literary Theory

2025-08-05

AI Summary

To address pervasive theme drift and logical discontinuity in long-form story generation, this paper proposes a multi-agent collaborative narrative generation framework. Methodologically: (1) a hierarchical memory mechanism—integrating short-term and long-term memory—is designed to dynamically anchor the core narrative theme; (2) a “theme–obstacle” dual-driven structure, grounded in classical narratology, explicitly models conflict evolution as the primary engine for plot progression; (3) dynamic knowledge graph expansion is fused with author–reader simulated dialogue feedback to jointly optimize content consistency and readability. Experimental results demonstrate that the proposed approach significantly outperforms existing baselines across three key dimensions—theme consistency, logical coherence, and plot vividness—and achieves state-of-the-art performance on multi-thousand-word story generation tasks.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Natural Language Processing: Generation
• Multiagent Systems: Adversarial Agents

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Topic discovery and tracking

Abstract

The generation of a long story consisting of several thousand words is a sub-task in the field of long text generation~(LTG). Previous research has addressed this challenge through outline-based generation, which employs a multi-stage method for generating outlines into stories. However, this approach suffers from two common issues: almost inevitable theme drift caused by the loss of memory of previous outlines, and tedious plots with incoherent logic that are less appealing to human readers. In this paper, we propose the multi-agent Story Generator structure to improve the multi-stage method, using large language models~(LLMs) as the core components of agents. To avoid theme drift, we introduce a memory storage model comprising two components: a long-term memory storage that identifies the most important memories, thereby preventing theme drift; and a short-term memory storage that retains the latest outlines from each generation round. To incorporate engaging elements into the story, we design a story theme obstacle framework based on literary narratology theory that introduces uncertain factors and evaluation criteria to generate outline. This framework calculates the similarity of the former storyline and enhances the appeal of the story by building a knowledge graph and integrating new node content. Additionally, we establish a multi-agent interaction stage to simulate writer-reader interaction through dialogue and revise the story text according to feedback, to ensure it remains consistent and logical. Evaluations against previous methods demonstrate that our approach can generate higher-quality long stories.

Problem

• Prevent theme drift in long story generation
• Enhance story appeal with coherent logic
• Improve multi-stage outline-based generation method

Innovation

• Multi-agent LLM structure for story generation
• Memory storage model prevents theme drift
• Knowledge graph enhances story appeal