教学生用控制思维稳住AI编程中的目标偏移问题
Human-in-the-Loop Control of Objective Drift in LLM-Assisted Computer Science Education
- 把规划与执行分离，先定验收标准和约束条件
- 三组对比实验显示结构化教学能显著降低目标漂移
- 适合想培养可控AI协作能力的高校计算机教育者
大型语言模型（LLMs）正越来越多地嵌入计算机科学教育，通过AI辅助编程工具实现。然而，这类工作流常出现目标漂移现象：局部看似合理的输出偏离了既定任务要求。现有教学多聚焦于特定工具的提示技巧，难以适应不断演进的AI平台。本文从以人为本的视角出发，将人类在回路（HITL）控制视为稳定教育问题，而非迈向AI自治的过渡阶段。借鉴系统工程与控制论思想，将目标与世界模型视为学生可配置的操作性构件，以稳定AI辅助工作。我们设计了一套试点本科计算机实验室课程，明确分离规划与执行，并训练学生在代码生成前设定验收标准与架构约束。部分实验中，引入与概念对齐的刻意漂移，以支持对规范违规的诊断与恢复。通过对三组设计（无结构使用AI、结构化规划、结构化规划+注入漂移）的敏感性功效分析，在真实班级规模约束下，确立了可检测的效果量。该研究为人类在回路教学提供了理论驱动、方法透明的基础，使控制能力可跨演化中的AI工具进行教授。
原文摘要 · Abstract (English)
Large language models (LLMs) are increasingly embedded in computer science education through AI-assisted programming tools, yet such workflows often exhibit objective drift, in which locally plausible outputs diverge from stated task specifications. Existing instructional responses frequently emphasize tool-specific prompting practices, limiting durability as AI platforms evolve. This paper adopts a human-centered stance, treating human-in-the-loop (HITL) control as a stable educational problem rather than a transitional step toward AI autonomy. Drawing on systems engineering and control-theoretic concepts, we frame objectives and world models as operational artifacts that students configure to stabilize AI-assisted work. We propose a pilot undergraduate CS laboratory curriculum that explicitly separates planning from execution and trains students to specify acceptance criteria and architectural constraints prior to code generation. In selected labs, the curriculum also introduces deliberate, concept-aligned drift to support diagnosis and recovery from specification violations. We report a sensitivity power analysis for a three-arm pilot design comparing unstructured AI use, structured planning, and structured planning with injected drift, establishing detectable effect sizes under realistic section-level constraints. The contribution is a theory-driven, methodologically explicit foundation for HITL pedagogy that renders control competencies teachable across evolving AI tools.
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。