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

• URL: http://arxiv.org/abs/2606.25632v1
• Date: Wed, 24 Jun 2026 09:37:49 GMT
• Title: Staying In Character: Perspective-Bounded Memory For Book-Based Role-Playing Agents
• Abstract summary: We propose REVERIEMEM, a three-layer memory architecture for book-based character agents.<n>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.<n>For evaluation, we construct KBF-QA, a 4,386-question benchmark over eight novels for testing knowledge boundaries.
• Score: 5.808135444478086
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 a ~ 79% win rate, suggesting that perspective-bounded memory improves both boundary fidelity and character-grounded narrative generation.

Related papers

• From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents [50.66268133366637]
  Current systems rely on persona-agnostic summarization, which records facts without persona-specific interpretation.<n>We introduce RoleMemo, a dataset featuring four reasoning tasks where the factual fragments must be interpreted through the persona to reach the correct answer.<n>We propose DualMem, which decouples memory into two streams: factual cognition and persona-conditioned insight.
  arXiv  Detail & Related papers  (2026-05-25T10:48:24Z)
• ReCap: Lightweight Referential Grounding for Coherent Story Visualization [11.022891519635834]
  ReCap is a lightweight consistency framework that improves character stability and visual fidelity without modifying the base diffusion backbone.<n>ReCap's CORE (COnditional frame REferencing) module treats anaphors, in our case pronouns, as visual anchors, activating only when characters are referred to by a pronoun and conditioning on the preceding frame to propagate visual identity.<n>We extend story visualization to human-centric narratives derived from real films, demonstrating the capability of ReCap beyond stylized cartoon domains.
  arXiv  Detail & Related papers  (2026-04-20T17:57:50Z)
• Think Before you Write: QA-Guided Reasoning for Character Descriptions in Books [52.08691427871138]
  We propose a training framework that decouples reasoning from generation.<n>Our approach consists of a reasoning model that produces a structured QA reasoning trace and a generation model that conditions on this trace to produce the final character description.
  arXiv  Detail & Related papers  (2026-04-13T13:19:56Z)
• Memory-Driven Role-Playing: Evaluation and Enhancement of Persona Knowledge Utilization in LLMs [8.377003560888905]
  We propose the Memory-Driven Role-Playing paradigm.<n>Inspired by Stanislavski's "emotional memory" acting theory, this paradigm frames persona knowledge as the LLM's internal memory store.<n>We contribute: MREval, a fine-grained evaluation framework assessing four memory-driven abilities; MRPrompt, a prompting architecture that guides structured memory retrieval and response generation; and MRBench, a bilingual benchmark for fine-grained diagnosis.
  arXiv  Detail & Related papers  (2026-03-14T07:12:42Z)
• Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers [0.42061757959666934]
  Large language model (LLM) agents increasingly operate in settings where a single context window is too small to capture what has happened.<n>Memory is what turns a stateless text generator into a genuinely adaptive agent.<n>This survey offers a structured account of how memory is designed, implemented, and evaluated in modern LLM-based agents.
  arXiv  Detail & Related papers  (2026-03-08T15:08:01Z)
• Living the Novel: A System for Generating Self-Training Timeline-Aware Conversational Agents from Novels [50.43968216132018]
  We present an end-to-end system that transforms any literary work into an immersive, multi-character conversational experience.<n>This system is designed to solve two fundamental challenges for LLM-driven characters.
  arXiv  Detail & Related papers  (2025-12-08T11:57:46Z)
• PsyMem: Fine-grained psychological alignment and Explicit Memory Control for Advanced Role-Playing LLMs [11.960470088030968]
  PsyMem is a novel framework integrating fine-grained psychological attributes and explicit memory control for role-playing.<n>By training Qwen2.5-7B-Instruct on our specially designed dataset, PsyMem-Qwen outperforms baseline models in role-playing.
  arXiv  Detail & Related papers  (2025-05-19T07:45:09Z)
• Memorization Over Reasoning? Exposing and Mitigating Verbatim Memorization in Large Language Models' Character Understanding Evaluation [9.783129095443758]
  Large Language Models (LLMs) have shown impressive performance in character understanding tasks.<n>We argue that 'gist memory' should be the primary mechanism for character understanding tasks.<n>We introduce a simple yet effective method to mitigate mechanized memorization in character understanding evaluations.
  arXiv  Detail & Related papers  (2024-12-18T22:04:56Z)
• CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds [74.02480671181685]
  Role-playing is a crucial capability of Large Language Models (LLMs)<n>Current evaluation methods fall short of adequately capturing the nuanced character traits and behaviors essential for authentic role-playing.<n>We propose CharacterBox, a simulation sandbox designed to generate situational fine-grained character behavior trajectories.
  arXiv  Detail & Related papers  (2024-12-07T12:09:35Z)
• Are Large Language Models Capable of Generating Human-Level Narratives? [114.34140090869175]
  This paper investigates the capability of LLMs in storytelling, focusing on narrative development and plot progression. We introduce a novel computational framework to analyze narratives through three discourse-level aspects. We show that explicit integration of discourse features can enhance storytelling, as is demonstrated by over 40% improvement in neural storytelling.
  arXiv  Detail & Related papers  (2024-07-18T08:02:49Z)
• Make-A-Story: Visual Memory Conditioned Consistent Story Generation [57.691064030235985]
  We propose a novel autoregressive diffusion-based framework with a visual memory module that implicitly captures the actor and background context. Our method outperforms prior state-of-the-art in generating frames with high visual quality. Our experiments for story generation on the MUGEN, the PororoSV and the FlintstonesSV dataset show that our method not only outperforms prior state-of-the-art in generating frames with high visual quality, but also models appropriate correspondences between the characters and the background.
  arXiv  Detail & Related papers  (2022-11-23T21:38:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.