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

arXiv:2611.14260 · cs.HC, cs.AI · Submitted 2026-11-10 · Read on arXiv

cs.HC, cs.AI

Submitted: 2026-11-10

Updated: 2026-11-10

License: http://creativecommons.org/licenses/by/4.0/

The gist: 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.

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.

Sources

Related papers