Research

Paper

AI LLM March 12, 2026

ELLA: Generative AI-Powered Social Robots for Early Language Development at Home

Authors

Victor Nikhil Antony, Shiye Cao, Shuning Wang, Chien-Ming Huang

Abstract

Early language development shapes children's later literacy and learning, yet many families have limited access to scalable, high-quality support at home. Recent advances in generative AI make it possible for social robots to move beyond scripted interactions and engage children in adaptive, conversational activities, but it remains unclear how to design such systems for pre-schoolers and how children engage with them over time in the home. We present ELLA (Early Language Learning Agent), an autonomous, generative AI-powered social robot that supports early language development through interactive storytelling, parent-selected language targets, and scaffolded dialogue. Using a multi-phased, human-centered process, we interviewed parents (n=7) and educators (n=5) and iteratively refined ELLA through twelve in-home design workshops. We then deployed ELLA with ten children for eight days. We report design insights from in-home workshops, characterize children's engagement and behaviors during deployment, and distill design implications for generative AI-powered social robots supporting early language learning at home.

Metadata

arXiv ID: 2603.12508
Provider: ARXIV
Primary Category: cs.HC
Published: 2026-03-12
Fetched: 2026-03-16 06:01

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.12508v1</id>\n    <title>ELLA: Generative AI-Powered Social Robots for Early Language Development at Home</title>\n    <updated>2026-03-12T22:55:54Z</updated>\n    <link href='https://arxiv.org/abs/2603.12508v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.12508v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Early language development shapes children's later literacy and learning, yet many families have limited access to scalable, high-quality support at home. Recent advances in generative AI make it possible for social robots to move beyond scripted interactions and engage children in adaptive, conversational activities, but it remains unclear how to design such systems for pre-schoolers and how children engage with them over time in the home. We present ELLA (Early Language Learning Agent), an autonomous, generative AI-powered social robot that supports early language development through interactive storytelling, parent-selected language targets, and scaffolded dialogue. Using a multi-phased, human-centered process, we interviewed parents (n=7) and educators (n=5) and iteratively refined ELLA through twelve in-home design workshops. We then deployed ELLA with ten children for eight days. We report design insights from in-home workshops, characterize children's engagement and behaviors during deployment, and distill design implications for generative AI-powered social robots supporting early language learning at home.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.HC'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-12T22:55:54Z</published>\n    <arxiv:primary_category term='cs.HC'/>\n    <author>\n      <name>Victor Nikhil Antony</name>\n    </author>\n    <author>\n      <name>Shiye Cao</name>\n    </author>\n    <author>\n      <name>Shuning Wang</name>\n    </author>\n    <author>\n      <name>Chien-Ming Huang</name>\n    </author>\n  </entry>"
}