arXiv：cs.AI· Mykhailo Kopytskyi, Jianhua Yang, Mir Seyedebrahimi·· 16 小时前
SocraticRepair：用规划引导的苏格拉底式辅导调试程序与修复误解
SocraticRepair: Planning-Guided Socratic Tutoring for Program Debugging and Misconception Repair
AI 导读
SocraticRepair 是一个规划引导的苏格拉底式辅导框架，用于程序调试与误解修复。该框架在 Python 领域基于四个预处理编程数据集构建合成多轮辅导对话，对 Qwen2.5-Coder-7B-Instruct 进行微调，并与通用 LLM 进行基准对比。实验显示其在逐步引导和提问质量上得分更高，同时大幅减少过早给出答案的情况，但可靠的教學计划生成仍是待解难题。
正文
Abstract:Large language models are increasingly used in computer science education. However, the teaching abilities of even the most powerful LLMs are limited: they tend to reveal the solution prematurely and may lose focus on the learner's current debugging objective. To address this, we introduce SocraticRepair, a planning-guided Socratic tutoring framework for program debugging and miscon- ception repair that adapts prior planning-guided tutoring work (Li et al., 2026b). The framework is instantiated in the Python programming domain by fine-tuning Qwen2.5-Coder-7B-Instruct on synthetic multi-turn tutoring dialogues constructed from four preprocessed programming datasets. The system is evaluated using a predefined set of independent metrics and benchmarked against a general-purpose LLM. The experiments show that SocraticRepair achieves higher scores on stepwise scaffolding and question quality while also substantially reducing premature solution disclosure. The results also identify reliable pedagogical plan generation as an important remaining challenge.
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.15204 [cs.AI] |
| (or arXiv:2610.15204v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.15204 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Mykhailo Kopytskyi [view email]
[v1]
Sat, 10 Oct 2026 22:28:56 UTC (60 KB)
来源：arXiv：cs.AI · arxiv.org