MIRACLE_Multi-Agent Intelligent Regulation to Advance Collaborative Learning Environment

📅 2026-05-12
📈 Citations: 0
Influential: 0
📄 PDF

career value

207K/year
🤖 AI Summary
This study addresses the widespread deficiency in socially shared regulation of learning (SSRL) among students in collaborative settings, which hinders effective planning, monitoring, and reflection. To tackle this challenge, the authors propose MIRACLE—the first multi-agent system specifically designed to support the entire SSRL process. MIRACLE integrates metacognitive regulation mechanisms with affective-motivational support modules and is embedded within the collaborative platform CocoNote to provide fine-grained, coordinated assistance for SSRL. Experimental results demonstrate that, compared to generic AI assistants, MIRACLE significantly enhances students’ performance across all phases of SSRL, fosters higher-quality collaborative outcomes, and receives strong student endorsement for its cognitive, regulatory, and emotional support.
📝 Abstract
Effective collaboration requires Socially Shared Regulation (SSRL), but students often lack these skills. This study introduces the MIRACLE (Multi-Agent Intelligent Regulation to Advance Collaborative Learning Environment) system, which supports SSRL by orchestrating metacognitive regulation and proactively providing emotional and motivational support. We conducted a quasi-experimental study with 90 fifth-grade students. The experimental group (n=42) used a collaborative platform CocoNote equipped with MIRACLE, while the control group (n=48) used the same platform with a general GPT assistant. Quantitative results show the MIRACLE group achieved significant gains across SSRL phases (Planning, Monitoring, Reflection) and produced higher-quality collaborative artifacts compared to the control group. Qualitative findings indicate students perceived MIRACLE as an effective facilitator for cognitive, regulatory, and emotional support. This study demonstrates that specialized, orchestrated AI systems are more effective than generic AI in enhancing SSRL.
Problem

Research questions and friction points this paper is trying to address.

Socially Shared Regulation
Collaborative Learning
Metacognitive Regulation
Emotional Support
Motivational Support
Innovation

Methods, ideas, or system contributions that make the work stand out.

Multi-Agent System
Socially Shared Regulation
Metacognitive Regulation
Collaborative Learning
AI in Education
🔎 Similar Papers
No similar papers found.