Story Generation in Multi-Agent Systems: A DynamicCollaboration Framework Based on Reinforcement Learning
Highlights in Science, Engineering and Technology · 26.06.2026 · 163 · 59-66
DOI: 10.54097/4m16y426 ↗Kurz gefasst
Fachartikel in der Zeitschrift Highlights in Science, Engineering and Technology, online erschienen am 26.06.2026. Verfasst von Yaolin Li. Die Arbeit nennt 15 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
In artificial intelligence, multi-agent systems excel in complex tasks requiring coordination. This paper presents a Multi-Agent Dynamic Collaboration Framework for story generation, tackling narrative coherence, diversity, and adaptability. Using GPT-2 agents for plot, dialogue, and description, a Transformer-based coordinator dynamically adjusts contributions via multi-head attention. PPO reinforcement learning optimizes behaviors with rewards based on BLEU, ROUGE, and entropy. Trained on ROCStories, the framework achieves BLEU 0.85, ROUGE-L 0.65, and perplexity 12.5, surpassing baselines. Human assessments show improved coherence and engagement. This advances AI creative writing and enables scalable applications in education, entertainment, and marketing for immersive narratives.
Zitieren
APA
Li, Y. (2026). Story Generation in Multi-Agent Systems: A DynamicCollaboration Framework Based on Reinforcement Learning. Highlights in Science, Engineering and Technology, 163, 59-66. https://doi.org/10.54097/4m16y426
Vancouver
Li Y. Story Generation in Multi-Agent Systems: A DynamicCollaboration Framework Based on Reinforcement Learning. Highlights in Science, Engineering and Technology. 2026;163:59-66. doi:10.54097/4m16y426
BibTeX
@article{Li2026,
author = {Li, Yaolin},
title = {Story Generation in Multi-Agent Systems: A DynamicCollaboration Framework Based on Reinforcement Learning},
journal = {Highlights in Science, Engineering and Technology},
year = {2026},
volume = {163},
pages = {59--66},
doi = {10.54097/4m16y426}
}
EUVIMED