Staying In Character: Perspective-Bounded Memory For Book-Based Role-Playing Agents
Xushuo Tang#, Junhe Zhang#, Zihan Yang, Yifu Tang, Sichao Li, Longbin Lai, Zhengyi Yang
RAIDS Lab Authors
Details
Research Area
Tags
Resources
Abstract
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 an approximately 79% win rate, suggesting that perspective-bounded memory improves both boundary fidelity and character-grounded narrative generation.
Author Affiliations
BibTeX
@misc{tang2026staying,
title = {Staying In Character: Perspective-Bounded Memory For Book-Based Role-Playing Agents},
author = {Xushuo Tang and Junhe Zhang and Zihan Yang and Yifu Tang and Sichao Li and Longbin Lai and Zhengyi Yang},
year = {2026},
eprint = {2606.25632},
archivePrefix = {arXiv},
primaryClass = {cs.CL},
url = {https://arxiv.org/abs/2606.25632}
}