arXiv cs.CL· Trystan Geoffre, Zheng Yuan, Thierry Geoffre·· 12 小时前AI 评分26
让推理过程可见：面向结构化推理任务自适应支架的配置感知诊断建模
Making Reasoning Visible: Configuration-Aware Diagnostic Modeling for Adaptive Scaffolding in Structured Reasoning Tasks
AI 导读
研究提出一个诊断框架，通过分析学生在交互式学习游戏中的动作序列，让逐步解题过程可见，并计算五个可解释的策略维度、从任务结构估计协调需求，将推理分为四种状态。基于 234 名学生完成 42 项词法句法练习的 36,234 次交互，研究发现推理策略主要随情境而非稳定特质变化（组内相关系数 = 0.14），74.6% 由高协调需求导致的失败在无干预下会再次失败。
正文
Abstract:Modeling the latent, multi-step reasoning processes of learners is a core challenge for adaptive tutoring systems, which often rely on simple right/wrong answers rather than understanding how students think. Instantiated here for grammatical reasoning, this study introduces a diagnostic framework that makes students' step-by-step problem-solving visible by analyzing their action sequences in an interactive learning game. The framework computes five interpretable strategy dimensions (e.g., systematic error correction, random guessing), estimates coordination demand from task structure and behavioral patterns, and classifies reasoning into four distinct states. Analyzing 36,234 interactions from 234 students working on 42 morphosyntactic exercises, we found that reasoning strategies vary primarily by context rather than stable traits (intraclass correlation = 0.14), and students show high persistence in unproductive states; specifically, 74.6% of failures driven by high coordination demand (rather than simple knowledge gaps) are followed by another failure without intervention. Our early warning model predicts validation success with strong accuracy (AUC = 0.826 using strategy patterns alone; 0.902 with additional sequential context) while avoiding circular reliance on current error counts. These findings demonstrate that making latent reasoning processes visible enables earlier, more targeted scaffolding that responds to how students are thinking rather than simply whether they succeed. While demonstrated in language learning, the framework provides a generalizable, interpretable architecture for diagnosing complex, structured reasoning in any domain.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.35609 [cs.CL] |
| (or arXiv:2610.35609v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35609 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Trystan Geoffre [view email]
[v1]
Mon, 26 Oct 2026 15:30:52 UTC (1,658 KB)
来源：arXiv cs.CL · arxiv.org