Skip to content

Role-Adaptive AI Companion Framework: a Modular Adaptive Agent that dynamically switches between Student Peer, Teacher Assistant, and Parent Advisor roles

Design · All designs
Evidence · 3 claims (3 for) · 1 study (1 causal), q2 · 0 of 1 report an effect size · 3 claims rest on one study

Description

The framework conceptualizes an AI companion as a Modular Adaptive Agent (MAA), inspired by Multi-Agent Systems role-differentiation principles, that "dynamically transitions between three primary roles: the ‘Student Peer’ (facilitating low-stakes dialogue), the ‘Teacher Assistant’ (providing diagnostic analytics), and the ‘Parent Advisor’ (offering actionable home-based guid - ance)." Its core principle is context-aware role adaptability: the agent perceives the user and pedagogical task and modulates its functions, interactional style, and communication register through a modular configuration mechanism, triggered by cues such as user login or task selection. The framework is grounded in scaffolding theory, Learning Companion System principles, and socio-ecological views of family involvement, and its transition logic is justified by the article's empirical competence-gap findings.

Design Implications

Context

Requirements

  • A unified data backbone with Role-Based Access Control and privacy-preserving data protocols so role-appropriate information is shared selectively
  • Triggers such as user identity or task selection to activate the appropriate role
  • Access to student interaction data, curriculum data, and student profiles for adaptation

Constraints

  • Conceptualized specifically for elementary reading education and book talk within programs like MSSR
  • The framework itself was not implemented or evaluated; the empirical study tested only a fixed single-role instantiation

Target Learners

  • Elementary school students in reading programs
  • Their teachers
  • Their parents

Learning Goals

  • Reading comprehension and reflective book talk
  • Factual recall, emotional response, and future-oriented application (4F dimensions)
  • Teacher instructional decision-making and parental support of reading at home

Claims

Examples

-

Key Sources

  • Liao, C.-Y. (2026). Beyond a single role: Justifying a role-adaptive framework for ai companions through a comparative study in elementary book talk. Education and Information Technologies. https://doi.org/10.1007/s10639-026-13958-6
Page metadata
Field Value
type design
id role-adaptive-ai-companion-framework-maa
title Role-Adaptive AI Companion Framework: a Modular Adaptive Agent that dynamically switches between Student Peer, Teacher Assistant, and Parent Advisor roles
description The framework conceptualizes an AI companion as a Modular Adaptive Agent (MAA), inspired by Multi-Agent Systems role-differentiation principles, that "dynamically transitions between three primary roles: the ‘Student...
status review
generated by process:settle-candidates on 2026-10-11
trust unverified — no one has confirmed this page's content
sources 1 — liao-2026

Frontmatter is the page's machine-readable record — see the Schema & Guide.