Skip to content
← Back to explorer

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 · Jun 24, 2026 · Citations: 0

How to use this page

Moderate trust

Use this for comparison and orientation, not as your only source.

Best use

Secondary protocol comparison source

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Evidence quality

Moderate

Derived from extracted protocol signals and abstract evidence.

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.

Should You Rely On This Paper?

This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.

Best use

Secondary protocol comparison source

Use if you need

A secondary eval reference to pair with stronger protocol papers.

Main weakness

No major weakness surfaced.

Trust level

Moderate

Usefulness score

65/100 • Medium

Useful as a secondary reference; validate protocol details against neighboring papers.

Human Feedback Signal

Detected

Evaluation Signal

Detected

Usefulness for eval research

Moderate-confidence candidate

Extraction confidence 70%

What We Could Verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

strong

Pairwise Preference

Directly usable for protocol triage.

"Recent LLM role-playing systems build character agents from novels by extracting characters, scenes, and relations."

Evaluation Modes

strong

Automatic Metrics

Includes extracted eval setup.

"Recent LLM role-playing systems build character agents from novels by extracting characters, scenes, and relations."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Recent LLM role-playing systems build character agents from novels by extracting characters, scenes, and relations."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Recent LLM role-playing systems build character agents from novels by extracting characters, scenes, and relations."

Reported Metrics

strong

Win rate

Useful for evaluation criteria comparison.

"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."

Human Feedback Details

  • Uses human feedback: Yes
  • Feedback types: Pairwise Preference
  • Rater population: Not reported
  • Unit of annotation: Pairwise
  • Expertise required: General

Evaluation Details

  • Evaluation modes: Automatic Metrics
  • Agentic eval: None
  • Quality controls: Not reported
  • Evidence quality: Moderate
  • Use this page as: Secondary protocol comparison source

Protocol And Measurement Signals

Benchmarks / Datasets

No benchmark or dataset names were extracted from the available abstract.

Reported Metrics

win rate

Research Brief

Metadata summary

Recent LLM role-playing systems build character agents from novels by extracting characters, scenes, and relations.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key Takeaways

  • 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.

Researcher Actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Research Summary

Contribution Summary

  • Recent LLM role-playing systems build character agents from novels by extracting characters, scenes, and relations.
  • To address these failures, we propose REVERIEMEM, a three-layer memory architecture for book-based character agents.
  • For evaluation, we construct KBF-QA, a 4,386-question benchmark over eight novels for testing knowledge boundaries.

Why It Matters For Eval

  • Recent LLM role-playing systems build character agents from novels by extracting characters, scenes, and relations.
  • To address these failures, we propose REVERIEMEM, a three-layer memory architecture for book-based character agents.

Researcher Checklist

  • Pass: Human feedback protocol is explicit

    Detected: Pairwise Preference

  • Pass: Evaluation mode is explicit

    Detected: Automatic Metrics

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Gap: Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Pass: Metric reporting is present

    Detected: win rate

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.

Get Started

The #1 talent network for AI training.

Self-Service
Post a job, get a curated shortlist
Manage your team directly on-platform
Managed Service
Most popular
Dedicated program lead for your project
We source, vet, and onboard your team
Freelance AI Trainer?
Join the #1 platform for finding AI training and data labeling work.