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

2026-01-28

AI Summary

This work addresses the challenge that existing AI tutoring systems struggle to support distributed planning and coordination required for multi-member collaborative learning in home environments. The paper introduces ParPal, the first system to incorporate multi-role collaborative planning into family learning contexts. ParPal leverages large language models (LLMs) to decompose learning goals into subtasks, allocates tasks while modeling caregivers’ temporal availability and expertise constraints, and enhances collaboration transparency and contribution visibility through a human-in-the-loop tutoring mechanism. The system integrates LLM-driven task decomposition, multi-participant availability modeling, and learning trajectory generation. Expert evaluations and a one-week in-situ deployment with 11 families demonstrate its effectiveness in improving coordination clarity and recognition of caregiving efforts, while also revealing systematic limitations of LLMs in role alignment, judgment of collaboration necessity, and modeling task feasibility.

Technology Category

• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Multiagent Systems: Multiagent Planning
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

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.

Problem

• family learning
• multi-actor collaboration
• AI tutoring
• distributed planning
• human-centred AI

Innovation

• multi-actor collaboration
• human-centred AI
• LLM-based planning
• family learning
• pedagogical structure