Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Prompting Destiny: Negotiating Socialization and Growth in an LLM-Mediated Speculative Gameworld

Mandi Yang, Zhiqi Gao, Yibo Meng, Dongyijie Primo Pan

TL;DR

This work addresses how educational guidance and socialization shift across developmental stages and how to render these dynamics legible in AI-mediated play. It proposes a staged four-season socialization arc in an LLM-driven RPG with delayed end-of-stage feedback (anti-visualization) to promote reflective reasoning. An empirical study with N=12 participants uses reflexive thematic analysis to reveal how players negotiate responsibility, role positioning, and moral tension. The study offers design guidance for translating sociological socialization models into reflective AI-mediated game systems and discusses practical implications such as entry load and the use of reflective artifacts.

Abstract

We present an LLM-mediated role-playing game that supports reflection on socialization, moral responsibility, and educational role positioning. Grounded in socialization theory, the game follows a four-season structure in which players guide a child prince through morally charged situations and compare the LLM-mediated NPC's differentiated responses across stages, helping them reason about how educational guidance shifts with socialization. To approximate real educational contexts and reduce score-chasing, the system hides real-time evaluative scores and provides delayed, end-of-stage growth feedback as reflective prompts. We conducted a user study (N=12) with gameplay logs and post-game interviews, analyzed via reflexive thematic analysis. Findings show how players negotiated responsibility and role positioning, and reveal an entry-load tension between open-ended expression and sustained engagement. We contribute design knowledge on translating sociological models of socialization into reflective AI-mediated game systems.

Prompting Destiny: Negotiating Socialization and Growth in an LLM-Mediated Speculative Gameworld

TL;DR

This work addresses how educational guidance and socialization shift across developmental stages and how to render these dynamics legible in AI-mediated play. It proposes a staged four-season socialization arc in an LLM-driven RPG with delayed end-of-stage feedback (anti-visualization) to promote reflective reasoning. An empirical study with N=12 participants uses reflexive thematic analysis to reveal how players negotiate responsibility, role positioning, and moral tension. The study offers design guidance for translating sociological socialization models into reflective AI-mediated game systems and discusses practical implications such as entry load and the use of reflective artifacts.

Abstract

We present an LLM-mediated role-playing game that supports reflection on socialization, moral responsibility, and educational role positioning. Grounded in socialization theory, the game follows a four-season structure in which players guide a child prince through morally charged situations and compare the LLM-mediated NPC's differentiated responses across stages, helping them reason about how educational guidance shifts with socialization. To approximate real educational contexts and reduce score-chasing, the system hides real-time evaluative scores and provides delayed, end-of-stage growth feedback as reflective prompts. We conducted a user study (N=12) with gameplay logs and post-game interviews, analyzed via reflexive thematic analysis. Findings show how players negotiated responsibility and role positioning, and reveal an entry-load tension between open-ended expression and sustained engagement. We contribute design knowledge on translating sociological models of socialization into reflective AI-mediated game systems.
Paper Structure (32 sections, 4 figures, 1 table)

This paper contains 32 sections, 4 figures, 1 table.

Table of Contents

  1. INTRODUCTION
  2. RELATED WORK
  3. METHODS
  4. Narrative and Interaction Design
  5. LLM-Based Feedback and System Implementation
  6. User Study
  7. Participants and Recruitment
  8. Procedure
  9. Analysis
  10. FINDINGS
  11. DISCUSSION
  12. Stage-Based Socialization and Shifts in Educational Role Positioning
  13. Delayed Feedback as Modeling Education as a Cumulative Social Process
  14. Limitations and Scope Conditions
  15. Conclusion
  16. ...and 17 more sections

Figures (4)

  • Figure 1: Screenshots of the game interface illustrating key moments in the staged role-play experience. From left to right: the opening scene that sets the narrative context; a control panel for stage progression and player actions; an activity selection view where players choose options for the prince; and an in-game dialogue scene with the NPC mentor and the prince.
  • Figure 2: An illustrative staged growth feedback summary generated by the system for one participant at the end of play. We use this artifact to prompt reflection in interviews; it is not treated as a validated psychometric measure.
  • Figure 3: Supplementary radar visualization summarizing system-generated growth feedback across participants. This figure is provided for reference and is not treated as a validated psychometric measure.
  • Figure 4: Supplementary radar visualization for a representative individual participant. This figure is provided for reference and is not treated as a validated psychometric measure.