# Symbolically Scaffolded Play: Designing Role-Sensitive Prompts for Generative NPC Dialogue

arXiv: https://arxiv.org/abs/2510.25820 · HTML: https://mlsanity.com/paper/2510.25820/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 48 references that are in the map.
- First posted on arXiv 29 Oct 2025.

## Builds on (most cited first, 16 of 16)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [TextWorld: A Learning Environment for Text-based Games](https://mlsanity.com/paper/1806.11532/) (2018)
- [Keep CALM and Explore: Language Models for Action Generation in Text-based Games](https://mlsanity.com/paper/2010.02903/) (2020)
- [Large Language Models and Games: A Survey and Roadmap](https://mlsanity.com/paper/2402.18659/) (2024)
- [Procedural Content Generation in Games: A Survey with Insights on Emerging LLM Integration](https://mlsanity.com/paper/2410.15644/) (2024)
- [Practical PCG Through Large Language Models](https://mlsanity.com/paper/2305.18243/) (2023)
- [GPT for Games: A Scoping Review (2020-2023)](https://mlsanity.com/paper/2404.17794/) (2024)
- [Dialogue Shaping: Empowering Agents through NPC Interaction](https://mlsanity.com/paper/2307.15833/) (2023)
- [GENEVA: GENErating and Visualizing branching narratives using LLMs](https://mlsanity.com/paper/2311.09213/) (2023)
- [The Procedural Content Generation Benchmark: An Open-source Testbed for Generative Challenges in Games](https://mlsanity.com/paper/2503.21474/) (2025)
- [Fuzzy, Symbolic, and Contextual: Enhancing LLM Instruction via Cognitive Scaffolding](https://mlsanity.com/paper/2508.21204/) (2025)
- [Cracking Aegis: An Adversarial LLM-based Game for Raising Awareness of Vulnerabilities in Privacy Protection](https://mlsanity.com/paper/2505.16954/) (2025)
- [Designing Smarter Conversational Agents for Kids: Lessons from Cognitive Work and Means-Ends Analyses](https://mlsanity.com/paper/2508.21209/) (2025)

## Built on by (most cited first, 1 of 1)

- [AI for Games in the Foundation Model Era](https://mlsanity.com/paper/2609.16679/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) promise to transform interactive games by enabling non-player characters (NPCs) to sustain unscripted dialogue. Yet it remains unclear whether constrained prompts actually improve player experience. We investigate this question through The Interview, a voice-based detective game powered by GPT-4o. A within-subjects usability study (N=10) compared high-constraint (HCP) and low-constraint (LCP) prompts, revealing no reliable experiential differences beyond sensitivity to technical breakdowns. Guided by these findings, we redesigned the HCP into a hybrid JSON+RAG scaffold and conducted a synthetic evaluation with an LLM judge, positioned as an early-stage complement to usability testing. Results uncovered a novel pattern: scaffolding effects were role-dependent: the Interviewer (quest-giver NPC) gained stability, while suspect NPCs lost improvisational believability. These findings overturn the assumption that tighter constraints inherently enhance play. Extending fuzzy-symbolic scaffolding, we introduce textitSymbolically Scaffolded Play, a framework in which symbolic structures are expressed as fuzzy, numerical boundaries that stabilize coherence where needed while preserving improvisation where surprise sustains engagement.