Beyond Automation: Socratic AI, Epistemic Agency, and the Implications of the Emergence of Orchestrated Multi-Agent Learning Architectures

TL;DR

This paper demonstrates that Socratic AI tutors can enhance critical and reflective thinking in students, and proposes a new multi-agent system approach for personalized, scalable, AI-supported education.

Contribution

It introduces the concept of orchestrated multi-agent systems for education and provides empirical evidence of Socratic AI's pedagogical benefits.

Findings

Students using Socratic AI reported greater critical thinking support.

The study shows potential for scalable, personalized AI-driven learning ecosystems.

System-level implications for higher education include changes in faculty roles and assessment practices.

Abstract

Generative AI is no longer a peripheral tool in higher education. It is rapidly evolving into a general-purpose infrastructure that reshapes how knowledge is generated, mediated, and validated. This paper presents findings from a controlled experiment evaluating a Socratic AI Tutor, a large language model designed to scaffold student research question development through structured dialogue grounded in constructivist theory. Conducted with 65 pre-service teacher students in Germany, the study compares interaction with the Socratic Tutor to engagement with an uninstructed AI chatbot. Students using the Socratic Tutor reported significantly greater support for critical, independent, and reflective thinking, suggesting that dialogic AI can stimulate metacognitive engagement and challenging recent narratives of de-skilling due to generative AI usage. These findings serve as a proof of concept for a broader pedagogical shift: the use of multi-agent systems (MAS) composed of specialised AI agents. To conceptualise this, we introduce the notion of orchestrated MAS, modular, pedagogically aligned agent constellations, curated by educators, that support diverse learning trajectories through differentiated roles and coordinated interaction. To anchor this shift, we propose an adapted offer-and-use model, in which students appropriate instructional offers from these agents. Beyond technical feasibility, we examine system-level implications for higher education institutions and students, including funding necessities, changes to faculty roles, curriculars, competencies and assessment practices. We conclude with a comparative cost-effectiveness analysis highlighting the scalability of such systems. In sum, this study contributes both empirical evidence and a conceptual roadmap for hybrid learning ecosystems that embed human-AI co-agency and pedagogical alignment.