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

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 \textit{Symbolically 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.

Fuzzy, Symbolic, and Contextual: Enhancing LLM Instruction via Cognitive Scaffolding

We study how architectural inductive biases influence the cognitive behavior of large language models (LLMs) in instructional dialogue. We introduce a symbolic scaffolding mechanism paired with a short-term memory schema designed to promote adaptive, structured reasoning in Socratic tutoring. Using controlled ablation across five system variants, we evaluate model outputs via expert-designed rubrics covering scaffolding, responsiveness, symbolic reasoning, and conversational memory. We present preliminary results using an LLM-based evaluation framework aligned to a cognitively grounded rubric. This enables scalable, systematic comparisons across architectural variants in early-stage experimentation. The preliminary results show that our full system consistently outperforms baseline variants. Analysis reveals that removing memory or symbolic structure degrades key cognitive behaviors, including abstraction, adaptive probing, and conceptual continuity. These findings support a processing-level account in which architectural scaffolds can reliably shape emergent instructional strategies in LLMs.

Designing Smarter Conversational Agents for Kids: Lessons from Cognitive Work and Means-Ends Analyses

This paper presents two studies on how Brazilian children (ages 9--11) use conversational agents (CAs) for schoolwork, discovery, and entertainment, and how structured scaffolds can enhance these interactions. In Study 1, a seven-week online investigation with 23 participants (children, parents, teachers) employed interviews, observations, and Cognitive Work Analysis to map children's information-processing flows, the role of more knowledgeable others, functional uses, contextual goals, and interaction patterns to inform conversation-tree design. We identified three CA functions: School, Discovery, Entertainment, and derived ``recipe'' scaffolds mirroring parent-child support. In Study 2, we prompted GPT-4o-mini on 1,200 simulated child-CA exchanges, comparing conversation-tree recipes based on structured-prompting to an unstructured baseline. Quantitative evaluation of readability, question count/depth/diversity, and coherence revealed gains for the recipe approach. Building on these findings, we offer design recommendations: scaffolded conversation-trees, child-dedicated profiles for personalized context, and caregiver-curated content. Our contributions include the first CWA application with Brazilian children, an empirical framework of child-CA information flows, and an LLM-scaffolding ``recipe'' (i.e., structured-prompting) for effective, scaffolded learning.

EXPLORA: A teacher-apprentice methodology for eliciting natural child-computer interactions

Investigating child-computer interactions within their contexts is vital for designing technology that caters to children's needs. However, determining what aspects of context are relevant for designing child-centric technology remains a challenge. We introduce EXPLORA, a multimodal, multistage online methodology comprising three pivotal stages: (1) building a teacher-apprentice relationship,(2) learning from child-teachers, and (3) assessing and reinforcing researcher-apprentice learning. Central to EXPLORA is the collection of attitudinal data through pre-observation interviews, offering researchers a deeper understanding of children's characteristics and contexts. This informs subsequent online observations, allowing researchers to focus on frequent interactions. Furthermore, researchers can validate preliminary assumptions with children. A means-ends analysis framework aids in the systematic analysis of data, shedding light on context, agency and homework-information searching processes children employ in their activities. To illustrate EXPLORA's capabilities, we present nine single case studies investigating Brazilian child-caregiver dyads' (children ages 9-11) use of technology in homework information-searching.