教育AI代理能力可按结构化维度系统提升，不只靠模型变大。
Scaling Laws for Educational AI Agents
- 用结构化配置文件定义代理角色与技能，实现能力渐进增长
- 330多个代理配置覆盖1100+知识点，性能随结构复杂度提升
- 适合教育AI研发者和个性化学习系统设计者参考
尽管大语言模型（LLM）在参数量、训练数据和计算资源上的缩放规律已被广泛研究，基于LLM的教育代理的缩放行为仍不明晰。我们提出教育代理能力不仅取决于底层模型规模，更通过一组结构性维度——即代理缩放定律——实现提升：角色定义清晰度、技能深度、工具完备性、运行时能力以及教育者知识注入。该框架的核心是AgentProfile，一种基于结构化JSON的规范，用于系统化地扩展教育代理能力。我们构建了EduClaw平台，这是一个以配置文件驱动的多代理系统，成功部署了330多个教育代理配置，涵盖K-12学科中超过1100个技能模块。实证观察表明，教育代理性能可预测地随配置结构丰富度提升。我们识别出两条互补的缩放路径——工具缩放与技能缩放——主张未来更强大的教育AI并非仅依赖更大模型，而是依托更健全的结构化能力体系。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。