Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.26461 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909816834752512 |
|---|---|
| author | Cheng, Yuyang Cai, Linyue Peng, Changwei Xu, Yumiao Bie, Rongfang Zhao, Yong |
| author_facet | Cheng, Yuyang Cai, Linyue Peng, Changwei Xu, Yumiao Bie, Rongfang Zhao, Yong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_26461 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CreAgentive: An Agent Workflow Driven Multi-Category Creative Generation Engine Cheng, Yuyang Cai, Linyue Peng, Changwei Xu, Yumiao Bie, Rongfang Zhao, Yong Computation and Language 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. |
| title | CreAgentive: An Agent Workflow Driven Multi-Category Creative Generation Engine |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2509.26461 |