构建可落地的LLM智能辅导系统，解决真实课程中教师难跟进学生数据的问题。
ITAS: A Multi-Agent Architecture for LLM-Based Intelligent Tutoring
- 分三层架构：教学层由三类专家代理+合成器组成，操作层用微服务管理状态与事件流。
- 试点中处理334次对话无幻觉，记录10628条学生行为事件，辅助教师发现两个关键问题。
- 专为应对教师信息盲区设计，适合高校开发可扩展的AI助教系统。
大语言模型辅导系统易在笔记本上搭建，却难投入真实课程运行。本文介绍ITAS（智能教学助理系统），一个在奥尔德尼大学量子计算研究生课程中运行一学期的多代理辅导系统。系统包含三层：教学层为三个并行专业代理（视频、代码、指导）加合成器，外加独立评分器评估提交作业的正确性与方法；操作层由四个Cloud Run微服务构成，会话状态存于Cloud SQL，交互事件通过Pub/Sub流至BigQuery；反馈层是窄范围对话代理，基于每课时匿名事件流回答教师提问，解决所谓“盲教师问题”——即LLM辅导积累的学生数据远超教师常规渠道可获取的范围。该架构直接回应早期原型的具体失败，描述了哪些改进被保留、哪些被放弃。我们报告了一次试点部署（五名学生、一门课程、一学期），作为系统行为证据而非学习成效证据：教学层在334次对话中未出现任务边界幻觉，操作层记录5个模块共10,628条事件，反馈层揭示两项教师中期干预的发现。我们不声称试点具有普适性，但认为所描述的系统是真实课程中运行的端到端LLM助学系统的可行方案。
原文摘要 · Abstract (English)
Large language model tutors are easy to build in a notebook and hard to run in a real course. We describe ITAS (Intelligent Teaching Assistant System), a multi-agent tutoring system that a graduate quantum computing course used for a semester at Old Dominion University. The system has three layers. The teaching layer is a Spoke-and-Wheel of three parallel specialist agents (Video, Code, Guidance) followed by a Synthesizer, plus a separate autograder that evaluates both the correctness and the approach of checkpoint submissions. The operational layer is four Cloud Run microservices with session state in Cloud SQL and interaction events streamed through Pub/Sub to BigQuery. The feedback layer is a narrow-scope conversational agent that answers instructor questions over per-lesson pseudonymized event streams, addressing what we call the Blind Instructor Problem: LLM tutors accumulate more data about students than the instructor can reach through routine channels. The architecture is a direct response to specific failures of an earlier prototype, and we describe which of those fixes carried forward and which were dropped for this iteration. We report on a pilot deployment (five students, one course, one semester) interpreted as system-behavior evidence rather than learning-outcome evidence: the teaching layer handled 334 chat turns without the task-boundary hallucinations that domain consolidation would have risked, the operational layer captured 10,628 events across five modules, and the feedback layer surfaced two findings the instructor acted on mid-semester. We do not claim the pilot generalizes. We do claim that the system as described is one workable answer to the question of what an LLM-based ITS needs to look like end-to-end to run in a real course.
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。