用3天时间在消费级显卡上部署出研究生水平的数学辅导AI。
From 50% to Mastery in 3 Days: A Low-Resource SOP for Localizing Graduate-Level AI Tutors via Shadow-RAG
- 用视觉语言模型清洗数据+新Shadow-RAG架构，仅需非专家3人日。
- 32B模型在结构化引导下从74%准确率跃升至90%，达精通水平。
- 适合教育科技团队快速低成本落地高阶AI助教系统。
在校园中部署高保真AI导师常受资源诅咒制约——需昂贵云GPU和大量数据工程。本文提出可复现的标准操作流程，突破此瓶颈。通过视觉-语言模型数据清洗策略与新型Shadow-RAG架构，仅用3人日非专家人力及可部署于单张消费级GPU的开源32B模型，成功本地化一名研究生级应用数学辅导系统。在完整研究生期末考试的试点研究中，发现显著涌现现象：零样本基线与标准检索方法在各代模型上均稳定在50%-60%准确率，而采用结构化推理引导的Shadow Agent使新一代32B模型性能从74%（朴素RAG）跃升至90%，达到精通水平；旧模型仅获约10%提升。这表明结构化引导是释放现代小型语言模型潜在能力的关键。本工作为普及化AI教育提供了一条成本可控、科学可靠的蓝图。
原文摘要 · Abstract (English)
Deploying high-fidelity AI tutors in schools is often blocked by the Resource Curse -- the need for expensive cloud GPUs and massive data engineering. In this practitioner report, we present a replicable Standard Operating Procedure that breaks this barrier. Using a Vision-Language Model data cleaning strategy and a novel Shadow-RAG architecture, we localized a graduate-level Applied Mathematics tutor using only 3 person-days of non-expert labor and open-weights 32B models deployable on a single consumer-grade GPU. Our pilot study on a full graduate-level final exam reveals a striking emergence phenomenon: while both zero-shot baselines and standard retrieval stagnate around 50-60% accuracy across model generations, the Shadow Agent, which provides structured reasoning guidance, triggers a massive capability surge in newer 32B models, boosting performance from 74% (Naive RAG) to mastery level (90%). In contrast, older models see only modest gains (~10%). This suggests that such guidance is the key to unlocking the latent power of modern small language models. This work offers a cost-effective, scientifically grounded blueprint for ubiquitous AI education.
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。