Learner-Tailored Program Repair: A Solution Generator with Iterative Edit-Driven Retrieval Enhancement

TL;DR

This paper introduces LRP, a novel program repair task tailored for learners, and proposes LSGEN, an iterative, retrieval-enhanced framework that improves bug fixing and explanation generation in programming coaching.

Contribution

The paper presents a new learner-specific program repair framework with iterative retrieval enhancement, advancing intelligent programming coaching systems.

Findings

Outperforms baseline methods significantly in bug fixing accuracy.

Effectively provides bug explanations alongside code repairs.

Iterative retrieval improves repair quality over single-pass methods.

Abstract

With the development of large language models (LLMs) in the field of programming, intelligent programming coaching systems have gained widespread attention. However, most research focuses on repairing the buggy code of programming learners without providing the underlying causes of the bugs. To address this gap, we introduce a novel task, namely LRP (Learner-Tailored Program Repair). We then propose a novel and effective framework, LSGEN (Learner-Tailored Solution Generator), to enhance program repair while offering the bug descriptions for the buggy code. In the first stage, we utilize a repair solution retrieval framework to construct a solution retrieval database and then employ an edit-driven code retrieval approach to retrieve valuable solutions, guiding LLMs in identifying and fixing the bugs in buggy code. In the second stage, we propose a solution-guided program repair method, which fixes the code and provides explanations under the guidance of retrieval solutions. Moreover, we propose an Iterative Retrieval Enhancement method that utilizes evaluation results of the generated code to iteratively optimize the retrieval direction and explore more suitable repair strategies, improving performance in practical programming coaching scenarios. The experimental results show that our approach outperforms a set of baselines by a large margin, validating the effectiveness of our framework for the newly proposed LPR task.