arXiv cs.AI· Ofri Elbaum, Amit Malik, Tomer Malkevich, Zohar Elyoseph, Adir Solomon, Rotem Dror, Oshrat Ayalon·· 3 小时前AI 评分33
Lilo：面向儿童数字交流的多智能体对话沙盒
Lilo: A Multi-Agent Conversational Sandbox for Children's Digital Communication
AI 导读
研究者推出 Lilo，一个让儿童练习群聊冲突对话的多智能体对话系统。儿童加入两个 AI 同伴的争论，由名为 Lilo 的导师角色通过 Stop-Think-Act 红绿灯进行指导。对 28 名 9-11 岁儿童的探索性研究显示，参与者应对不友善消息的自我效能感显著提升，且因所写内容不会被追责而感到可以放心尝试。
正文 · 原文
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.
| Subjects: | Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.14260 [cs.HC] |
| (or arXiv:2611.14260v1 [cs.HC] for this version) | |
| https://doi.org/10.48550/arXiv.2611.14260 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Oshrat Ayalon [view email]
[v1]
Tue, 10 Nov 2026 16:07:13 UTC (4,358 KB)
来源：arXiv cs.AI · arxiv.org