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

arXiv: https://arxiv.org/abs/2508.21209 · HTML: https://mlsanity.com/paper/2508.21209/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 9 of its 71 references that are in the map.
- First posted on arXiv 28 Aug 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 9 of 9)

- [What Makes a Good Conversation? Challenges in Designing Truly Conversational Agents](https://mlsanity.com/paper/1901.06525/) (2019)
- [PeerGPT: Probing the Roles of LLM-based Peer Agents as Team Moderators and Participants in Children's Collaborative Learning](https://mlsanity.com/paper/2403.14227/) (2024)
- [Pedagogical Agents for Fostering Question-Asking Skills in Children](https://mlsanity.com/paper/2004.03472/) (2020)
- [SkillBot: Identifying Risky Content for Children in Alexa Skills](https://mlsanity.com/paper/2102.03382/) (2021)
- ["It's Not a Replacement:" Enabling Parent-Robot Collaboration to Support In-Home Learning Experiences of Young Children](https://mlsanity.com/paper/2403.14041/) (2024)
- [What Do Children and Parents Want and Perceive in Conversational Agents? Towards Transparent, Trustworthy, Democratized Agents](https://mlsanity.com/paper/2209.07862/) (2022)
- ["My Unconditional Homework Buddy:'' Exploring Children's Preferences for a Homework Companion Robot](https://mlsanity.com/paper/2305.02720/) (2023)
- [Hybrid Models for Facial Emotion Recognition in Children](https://mlsanity.com/paper/2308.12547/) (2023)
- [EXPLORA: A teacher-apprentice methodology for eliciting natural child-computer interactions](https://mlsanity.com/paper/2403.17264/) (2024)

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

- [Symbolically Scaffolded Play: Designing Role-Sensitive Prompts for Generative NPC Dialogue](https://mlsanity.com/paper/2510.25820/) (2025)

## Abstract (arXiv)

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.