arXiv cs.CL· Ruisheng Sun, Jiaqi Shao, Weijia Han, Linxi Ju, Yunzhen Zhang, Binyan Sun, Rong Chen, Benjamin Blas Maristany, Ye Lu, Rui Hu, Ernesto Escobar, Bing Luo·· 11 小时前AI 评分20
基于 LLM 的自演化叙事系统：实时自适应与长期优化框架
Towards Self-Evolving Narrative Systems: Real-Time Adaptation and Long-Term Optimization with LLMs
AI 导读
研究者提出一种混合叙事框架，通过语义相似度对齐动态平衡预写内容与 LLM 实时生成，以兼顾作者控制与玩家能动性。该框架还引入反馈驱动的自演化优化机制，利用 in-context learning 迭代精炼提示词，无需人工提示词工程。案例研究与参与者评估显示，该框架在保持玩家能动性的同时提升了叙事连贯性。
正文 · 原文
Authors:Ruisheng Sun, Jiaqi Shao, Weijia Han, Linxi Ju, Yunzhen Zhang, Binyan Sun, Rong Chen, Benjamin Blas Maristany, Ye Lu, Rui Hu, Ernesto Escobar, Bing Luo
Abstract:Traditional interactive narrative systems offer strong authorial control and structural coherence but often restrict player agency. In contrast, LLM-driven narratives enable open-ended generation and greater flexibility, yet frequently suffer from inconsistency and diminished narrative control. To navigate this trade-off, we propose a hybrid narrative framework that dynamically balances pre-authored content with real-time LLM generation via semantic similarity alignment. Additionally, sustaining narrative quality over extended gameplay remains a core challenge in LLM-based storytelling. To address this, we introduce a self-evolving, feedback-driven optimization framework that leverages in-context learning to iteratively refine prompts, eliminating the need for manual prompt engineering. Through a case study and participant-based evaluation, we show that our framework enhances narrative coherence while preserving player agency, effectively aligning generated content with both authorial intent and evolving player behavior.
| Comments: | Under review at the ACL Rolling Review (ARR) October 2026 cycle |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.01954 [cs.CL] |
| (or arXiv:2611.01954v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.01954 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ruisheng Sun [view email]
[v1]
Sun, 1 Nov 2026 14:33:52 UTC (12,309 KB)
来源：arXiv cs.CL · arxiv.org