cs.HCNov 10, 2026

Lilo: A Multi-Agent Conversational Sandbox for Children's Digital Communication

Authors: Ofri Elbaum, Amit Malik, Tomer Malkevich, Zohar Elyoseph, Adir Solomon, Rotem Dror, Oshrat Ayalon

Organizations: University of Haifa, Israel

Abstract

Children's peer conflicts increasingly play out in group chats, where tone and timing are stripped away, and a hurtful message is easier to send than to say aloud. We present Lilo, a multi-agent conversational system that lets children practice such conversations, so they are better prepared when they encounter them in real digital communication. In Lilo, the child joins two AI-driven peers mid-argument, coached by a mentor character, also named Lilo, through a Stop-Think-Act traffic light. Through an exploratory study with 28 children (aged 9-11), we examine how children engage with Lilo's simulated peer conflict and the mentor's traffic-light interventions. The study included an intervention with Lilo, surveys before and after the intervention, and exit interviews. Participants reported significantly higher self-efficacy for coping with unpleasant messages after their interaction with Lilo. They felt safe experimenting, knowing nothing they wrote would be held against them.

Figures & tables

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. AYO: A Safe and Privacy-Preserving Platform for Studying Children's Interaction with LLMs

    Nov 5, 2026Huiwen Alex Yang, Rachel Skwersky, Bill D. Thompson +1Human-AI InteractionAI Safety

  2. Persona and Persuasive Framing in AI Voice Agents: A 2×22\times2 Field Experiment with Children

    Sep 30, 2026Thilo Tamme, David Steck, Anton HantelHuman-AI InteractionFraming Effects in Language Models

  3. Tinker Tales: A Tangible Dialogue System for Child-AI Co-Creative Storytelling

    Feb 4, 2026Nayoung Choi, Jiseung Hong, Peace Cyebukayire +2Interactive StorytellingConversational Agents