Scaling Laws for Educational AI Agents

TL;DR

This paper introduces the Agent Scaling Law, a framework for scaling educational AI agents through structured profiles and capabilities, demonstrated with a multi-agent platform and extensive profiles across K-12 subjects.

Contribution

It proposes a new scaling law for educational AI agents based on structured profile dimensions, and implements a platform to validate this approach.

Findings

Educational agent performance scales with profile richness.

Structured capability systems are crucial for scaling educational AI.

Tool and skill scaling axes are promising directions for future work.

Abstract

While scaling laws for Large Language Models (LLMs) have been extensively studied along dimensions of model parameters, training data, and compute, the scaling behavior of LLM-based educational agents remains unexplored. We propose that educational agent capability scales not merely with the underlying model size, but through structured dimensions that we collectively term the Agent Scaling Law: role definition clarity, skill depth, tool completeness, runtime capability, and educator expertise injection. Central to this framework is AgentProfile, a structured JSON-based specification that serves as the mechanism enabling systematic capability growth of educational agents. We present EduClaw, a profile-driven multi-agent platform that operationalizes this scaling law, demonstrating its effectiveness through the construction and deployment of 330+ educational agent profiles encompassing 1,100+ skill modules across K-12 subjects. Our empirical observations suggest that educational agent performance scales predictably with profile structural richness. We identify two complementary scaling axes -- Tool Scaling and Skill Scaling -- as future directions, arguing that the path to more capable educational AI lies not solely in larger models, but in stronger structured capability systems.