让角色只说符合视角的台词，解决长篇角色扮演中的事实越界和风格单一问题。
Staying In Character: Perspective-Bounded Memory For Book-Based Role-Playing Agents
- 分层记忆：第一人称场景、可见性标注事实、情境化言行模式
- 知识边界准确率提升34.6个百分点，对战胜率接近79%
- 适合需要高一致性角色扮演的应用，如互动小说与虚拟陪练
近期基于小说构建角色代理的LLM系统虽能提取人物、场景与关系，但长篇角色扮演常出现两种缺陷：事实越界（角色使用其视角外的知识）与风格单调（固定口吻削弱人物个性）。为此，本文提出REVERIEMEM，一种三层次记忆架构：情景层存储第一人称场景记忆；语义层存储带可视性标签的事实；人格层存储情境依赖的言谈与行为模式。为评估，构建KBF-QA基准，覆盖八部小说共4,386个问题，用于检验知识边界。REVERIEMEM在知识边界保真度上较最强基线提升34.6个百分点。在BOOKWORLD五维叙事对比协议中，取得约79%胜率，表明视角限定记忆可同时提升边界准确性与角色化叙事质量。
原文摘要 · Abstract (English)
Recent LLM role-playing systems build character agents from novels by extracting characters, scenes, and relations. Yet long-narrative role-playing suffers from two failures: Factual Overreach, where shared retrieval or parametric memory lets a character use facts outside its perspective, and Stylistic Monotony, where profile descriptions flatten a character into a fixed voice. To address these failures, we propose REVERIEMEM, a three-layer memory architecture for book-based character agents. The episodic layer stores first-person scene memories; the semantic layer stores visibility-tagged facts; and the personality layer stores situation-dependent speech and behaviour patterns. For evaluation, we construct KBF-QA, a 4,386-question benchmark over eight novels for testing knowledge boundaries. REVERIEMEM improves Knowledge Boundary Fidelity by 34.6 percentage points over the strongest prior method. On BOOKWORLD's five-dimension pairwise narrative protocol, REVERIEMEM achieves a ~ 79% win rate, suggesting that perspective-bounded memory improves both boundary fidelity and character-grounded narrative generation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。