arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.20650cs.AIcs.CY
收藏

从50%到精通:一种低资源SOP,通过影子RAG本地化研究生级AI导师

From 50% to Mastery in 3 Days: A Low-Resource SOP for Localizing Graduate-Level AI Tutors via Shadow-RAG

School of Mechanics and Engineering Science, Peking University, Beijing, 100871, China(北京理工大学机械与工程科学学院);Readraft Intelligent Technology Co., Ltd., China(读raft智能科技有限公司);Graduate School of Education, Peking University, Beijing, 100871, China(北京大学教育学院);AI for Science Institute, Beijing, 100080, China(AI for Science研究院)

Zonglin Yang, J. -H. Xie, Lining Zhang, Jiyou Jia, Zhi-X. Chen

AI总结:

本文提出一种低成本SOP,利用影子RAG架构和数据清洗策略,在3人天内本地化研究生级AI导师,使32B模型性能从74%提升至90%。

摘要:

在学校部署高保真AI导师常受资源诅咒阻碍——需要昂贵的云GPU和大量数据工程。本文提出一种可复制的标准操作程序,通过视觉-语言模型数据清洗策略和新型影子RAG架构,仅用3人天非专家劳动和开源32B模型在单个消费级GPU上本地化研究生级应用数学导师。全研究生级期末考试试点研究表明,零样本基线和标准检索在模型生成中稳定在50-60%准确率,而提供结构化推理指导的影子代理在较新的32B模型中触发巨大能力提升,使性能从74%(朴素RAG)提升至精通水平(90%)。相比之下,旧模型仅获得小幅提升(约10%)。这表明此类指导是释放现代小型语言模型潜在能力的关键。本文提供了一种成本效益高且科学严谨的蓝图,推动AI教育的普及。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑