Scaling Laws for Educational AI Agents

TL;DR

E EduClaw, a profile-driven multi-agent platform that operationalizes this scaling law, is presented, demonstrating its effectiveness through the construction and deployment of 330+ educational agent profiles encompassing 1,100+ skill modules across K-12 subjects.

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.

Figures (6)

• Figure 1: EduClaw platform main page. The sidebar provides access to the agent repository, agent construction, and skill repository. The platform supports AgentProfile-based automated agent generation and management.
• Figure 2: End-to-end pipeline from one-sentence description to running educational agent. Stages 1 and 2 are LLM-powered (dashed arrows); Stage 3 is deterministic construction.
• Figure 3: EduClaw agent construction interface. From a one-sentence input, the system generates an AgentProfile, matches skills from the library (shown as tags), and produces a running agent.
• Figure 4: EduClaw three-tier architecture. AgentProfiles provide declarative specifications that drive agent construction; the management layer orchestrates process lifecycle and request routing; each agent runs as an isolated Open Claw runtime instance.
• Figure 5: EduClaw agent repository. Agents are organized by subject and filterable by grade level.