Staying In Character: Perspective-Bounded Memory For Book-Based Role-Playing Agents

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Xushuo Tang, Junhe Zhang, Zihan Yang, Yifu Tang, Sichao Li, Longbin Lai, Zhengyi Yang
• Venue: arXiv: cs.CL
• Published: 2026-06-24
• Collected: 2026-06-25
• URL: http://arxiv.org/abs/2606.25632v1
• PDF: https://arxiv.org/pdf/2606.25632v1
• DOI: UNKNOWN

Plain-Language Brief

Researchers propose a new memory architecture called REVERIEMEM for book-based role-playing agents to improve the accuracy of the characters' knowledge boundaries and reduce stylistic monotony. They evaluate their model on a question benchmark and a narrative protocol, showing improvements over existing methods.

What the Document Says

• The research introduces REVERIEMEM, a three-layer memory architecture for book-based role-playing agents.
• The episodic layer stores first-person scene memories.
• The semantic layer stores visibility-tagged facts.
• The personality layer stores situation-dependent speech and behaviour patterns.
• A benchmark of 4,386 questions over eight novels was constructed to test 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.

Key Concepts Mentioned

• REVERIEMEM
• role-playing agents
• book-based
• perspective-bounded memory
• knowledge boundaries
• Stylistic Monotony
• Factual Overreach

Claims Made by the Document

• REVERIEMEM improves Knowledge Boundary Fidelity.
• REVERIEMEM achieves a ~79% win rate on BOOKWORLD's five-dimension pairwise narrative protocol.

Evidence Used

• Improves Knowledge Boundary Fidelity by 34.6 percentage points over the strongest prior method.
• ~79% win rate on BOOKWORLD's five-dimension pairwise narrative protocol

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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.