CtrlNews: LLM-based Multi-Agent Controllable News Writing via Knowledge Gravitational Field

Yifei Xu, Yingjie Zong, Wang Zhonghua, Sirui Wu, Yuan Rao, Dan Zhang, Shuiguang Deng


Abstract
News writing empowered by large language models (LLMs) has emerged as a prevalent trend due to their efficiency and scalability. This paradigm necessitates dynamic information acquisition, knowledge structuring, and precise viewpoint articulation. However, current approaches often rely on superficially retrieved information and oversimplified knowledge enumeration, resulting in shallow, repetitive, and unordered outputs. Additionally, the lack of controllability over narrative viewpoints fails to align with user-defined preferences. To address these limitations, we propose an LLM-based multi-agent controllable news writing framework termed CtrlNews. The framework simulates expert questioning through automated role assignment and question generation followed by a three-layer hierarchical gravitational graph iteratively refined via expansion-reflection cycles. Besides, we elaborate a fine-grained viewpoint control mechanism to precisely regulate bias, emotion, and exaggeration attributes. When composing long-form news articles, the controlled viewpoints are extended via emotion-preserving composition and self-reflection refinement to ensure the consistency of viewpoint control and prevent the dilution of the control effect. Experiments on quality and control effect evaluation, news dissemination effect assessment, and human evaluation demonstrate significant improvements across multiple metrics compared to existing methods.
Anthology ID:
2025.findings-emnlp.461
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8668–8705
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.461/
DOI:
Bibkey:
Cite (ACL):
Yifei Xu, Yingjie Zong, Wang Zhonghua, Sirui Wu, Yuan Rao, Dan Zhang, and Shuiguang Deng. 2025. CtrlNews: LLM-based Multi-Agent Controllable News Writing via Knowledge Gravitational Field. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 8668–8705, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
CtrlNews: LLM-based Multi-Agent Controllable News Writing via Knowledge Gravitational Field (Xu et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.461.pdf
Checklist:
 2025.findings-emnlp.461.checklist.pdf