发表机构
Ritsumeikan University; Tampere University（立命馆大学; 坦佩雷大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
SENSE是一个状态感知框架，通过集成MIND架构和路径感知模块，从最小输入生成多路径情感丰富的分支视觉小说，并在叙事多样性和资产集成上优于基线。
AI 中文摘要
本文提出了SENSE，一个用于生成具有多轨道情感导航的可玩分支视觉小说的状态感知框架。该框架集成了名为MIND的基于状态的叙事架构、一个结构分析器以及一个路径感知的上下文管理模块，从而生成既结构连贯又情感丰富的叙事内容。从最简的高级输入出发，SENSE能够生成多条交叉的路线，同时保持角色一致性和叙事因果性。使用LLM评判器、情感指标和视觉评估进行的评估表明，SENSE在叙事多样性和稳健的资产集成方面优于基线方法，而初步的人类试验显示其在情感保真度方面有方向性的改进，同时享受度相当。
英文摘要
This paper presents SENSE, a state-aware framework for generating playable branching visual novels with multi-track emotional navigation. Integrating a state-based narrative architecture called MIND, a structure analyzer, and a path-aware context management module, SENSE produces narratives that are both structurally coherent and emotionally rich. From minimal high-level inputs, it generates multiple intersecting routes while preserving character consistency and narrative causality. Evaluations using LLM judges, affective metrics, and visual assessments indicate SENSE outperforms baselines in narrative diversity and robust asset integration, while preliminary human trials show directional improvements in emotional fidelity alongside comparable enjoyment.
Journal refIEEE Transactions on Games ( Early Access ), 2026, 1 - 11
