A Human-Centred AI System for Multi-Actor Planning and Collaboration in Family Learning

TL;DR

This paper presents ParPal, an AI system designed to support multi-actor family learning by decomposing goals, allocating tasks, and providing caregiver support, while analyzing current LLM limitations in real-world educational settings.

Contribution

Introduction of ParPal, a human-centered AI system for multi-actor family learning that addresses planning, coordination, and pedagogical challenges using LLMs.

Findings

ParPal improves coordination clarity among caregivers.

Expert evaluation reveals systematic failures in current LLM planning.

Real-world deployment exposes limitations in LLM reasoning about collaboration and constraints.

Abstract

Family learning takes place in everyday routines where children and caregivers read, practice, and develop new skills together. Despite growing interest in AI tutors, most existing systems are designed for single learners or classroom settings and do not address the distributed planning, coordination, and execution demands of learning at home. This paper introduces ParPal, a human-centred, LLM-powered system that supports multi-actor family learning by decomposing learning goals into actionable subtasks, allocating them across caregivers under realistic availability and expertise constraints, and providing caregiver-in-the-loop tutoring support with visibility into individual and collective contributions. Through expert evaluation of generated weekly learning plans and a one-week field deployment with 11 families, we identify systematic failure modes in current LLM-based planning, including misalignment with role expertise, unnecessary or costly collaboration, missing pedagogical learning trajectories, and physically or temporally infeasible tasks. While ParPal improves coordination clarity and recognition of caregiving effort, these findings expose fundamental limitations in how current LLMs operationalize pedagogical knowledge, reason about collaboration, and account for real-world, embodied constraints. We discuss implications for human-centred AI design and AI methodology, positioning multi-actor family learning as a critical testbed for advancing planning, adaptation, and pedagogical structure in next-generation AI systems.