Beyond the AI Tutor: Social Learning with LLM Agents

TL;DR

This paper explores multi-agent LLM setups in educational contexts, demonstrating that combining a tutor with peer-like agents improves learning outcomes and diversity of ideas over single-agent systems.

Contribution

It provides one of the first controlled studies showing how multi-agent LLM configurations can enhance learning through social interaction effects.

Findings

Participants with both tutor and peer LLMs achieved higher test accuracy.

Two-agent LLM setups prevented idea homogeneity in essay writing.

Multi-agent environments can unlock collaborative learning benefits.

Abstract

Most AI-based educational tools today adopt a one-on-one tutoring paradigm, pairing a single LLM with a single learner. Yet decades of learning science research suggest that multi-party interaction -- through peer modeling, co-construction, and exposure to diverse perspectives -- can produce learning benefits that dyadic tutoring alone cannot. In this paper, we investigate whether multi-agent LLM configurations can enhance learning outcomes beyond what a single LLM tutor provides. We present two controlled experiments spanning distinct learning contexts. In a convergent problem-solving study ($N=315$), participants tackle SAT-level math problems in a 2$\times$2 design that varies the presence of an LLM tutor and LLM peers, each making different kinds of errors (conceptual vs.\ arithmetic); participants who interacted with both a tutor and peers achieved the highest unassisted test accuracy. In a divergent composition study ($N=247$), participants write argumentative and creative essays with either no AI assistance, a single LLM (Claude or ChatGPT), or both Claude and ChatGPT together; while both LLM conditions improved essay quality, only the two-agent condition avoided the idea-level homogeneity that single-model assistance was found to produce. Together, these studies offer one of the first controlled investigations of multi-agent LLM learning environments, probing whether the move from one-on-one AI tutoring toward richer agent configurations can unlock the collaborative and observational benefits long documented in human social learning research.