CreAgentive: An Agent Workflow Driven Multi-Category Creative Generation Engine

2025-09-30

AI Summary

Current large language models face four key bottlenecks in creative writing: limited thematic diversity, constrained output length, weak narrative coherence, and poor support for complex structural elements. To address these challenges, we propose a multi-agent workflow-based creative generation engine. Our core contributions are threefold: (1) a story archetype representation that decouples narrative logic from stylistic expression; (2) a semantic knowledge graph composed of character–event–environment triples to enable structured narrative reasoning; and (3) a three-stage, long- and short-horizon goal–coordinated multi-agent dialogue mechanism, enabling stable long-text generation with advanced narrative controls such as foreshadowing and retrospective consistency. Experiments demonstrate that our method efficiently generates multi-thousand-chapter narratives, significantly outperforming strong baselines across diverse genres in quality, at a cost under $1 per hundred chapters, achieving overall fidelity approaching human-level novel authorship.

Technology Category

• Natural Language Processing: Generation
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Humans and AI: Game Design — Procedural Content Generation & Storytelling

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

We present CreAgentive, an agent workflow driven multi-category creative generation engine that addresses four key limitations of contemporary large language models in writing stories, drama and other categories of creatives: restricted genre diversity, insufficient output length, weak narrative coherence, and inability to enforce complex structural constructs. At its core, CreAgentive employs a Story Prototype, which is a genre-agnostic, knowledge graph-based narrative representation that decouples story logic from stylistic realization by encoding characters, events, and environments as semantic triples. CreAgentive engages a three-stage agent workflow that comprises: an Initialization Stage that constructs a user-specified narrative skeleton; a Generation Stage in which long- and short-term objectives guide multi-agent dialogues to instantiate the Story Prototype; a Writing Stage that leverages this prototype to produce multi-genre text with advanced structures such as retrospection and foreshadowing. This architecture reduces storage redundancy and overcomes the typical bottlenecks of long-form generation. In extensive experiments, CreAgentive generates thousands of chapters with stable quality and low cost (less than $1 per 100 chapters) using a general-purpose backbone model. To evaluate performance, we define a two-dimensional framework with 10 narrative indicators measuring both quality and length. Results show that CreAgentive consistently outperforms strong baselines and achieves robust performance across diverse genres, approaching the quality of human-authored novels.

Problem

• Overcoming limited genre diversity in creative writing generation
• Addressing weak narrative coherence and insufficient output length
• Solving inability to enforce complex structural constructs in stories

Innovation

• Agent workflow driven creative generation engine
• Story Prototype with knowledge graph narrative representation
• Three-stage agent workflow for multi-genre text generation