Related papers: BoostAPR: Boosting Automated Program Repair via Ex…
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…
Human-designed reward functions for reinforcement learning (RL) agents are frequently misaligned with the humans' true, unobservable objectives, and thus act only as proxies. Optimizing for a misspecified proxy reward function often induces…
Providing personalized and timely feedback for student's programming assignments is useful for programming education. Automated program repair (APR) techniques have been used to fix the bugs in programming assignments, where the Large…
Automatic Program Repair (APR) aims at fixing buggy source code with less manual debugging efforts, which plays a vital role in improving software reliability and development productivity. Recent APR works have achieved remarkable progress…
Large language models have shown remarkable aptitude in code generation, but still struggle to perform complex tasks. Self-repair -- in which the model debugs and repairs its own code -- has recently become a popular way to boost…
We consider the problem of learning to repair programs from diagnostic feedback (e.g., compiler error messages). Program repair is challenging for two reasons: First, it requires reasoning and tracking symbols across source code and…
The existing deep learning (DL)-based automated program repair (APR) models are limited in fixing general software defects. % We present {\tool}, a DL-based approach that supports fixing for the general bugs that require dependent changes…
This paper presents a novel end-to-end approach to program repair based on sequence-to-sequence learning. We devise, implement, and evaluate a system, called SequenceR, for fixing bugs based on sequence-to-sequence learning on source code.…
Reinforcement learning (RL) has become a promising paradigm for optimizing Retrieval-Augmented Generation (RAG) in complex reasoning tasks. However, traditional outcome-based RL approaches often suffer from reward sparsity and inefficient…
Prompt-injected memory can improve reasoning without updating model weights, but it also creates a control problem: retrieved content helps only when it is applied in the right state. We study this problem in a strict training-free setting…
Large language model-(LLM) based automated program repair (APR) techniques have shown promising results in resolving real-world GitHub issue tasks. Existing APR systems are primarily evaluated in unimodal settings (e.g., SWE-bench).…
Automated Program Repair (APR) aims to enhance software reliability by automatically generating bug-fixing patches. Recent work has improved the state-of-the-art of APR by fine-tuning pre-trained large language models (LLMs), such as…
Current automated program repair (APR) techniques are far from being practical and useful enough to be considered for realistic debugging. They rely on unrealistic assumptions including the requirement of a comprehensive suite of test cases…
Large Language Models (LLMs) perform well on automatic program repair (APR) for high-resource programming languages (HRPLs), but their effectiveness drops sharply in low-resource programming languages (LRPLs), due to a lack of sufficient…
Automated program repair (APR) aims to automatize the process of repairing software bugs in order to reduce the cost of maintaining software programs. Moreover, the success (given by the accuracy metric) of APR approaches has increased in…
To date, over 40 Automated Program Repair (APR) tools have been designed with varying bug-fixing strategies, which have been demonstrated to have complementary performance in terms of being effective for different bug classes. Intuitively,…
Reinforcement learning agents learn by encouraging behaviours which maximize their total reward, usually provided by the environment. In many environments, however, the reward is provided after a series of actions rather than each single…
We revisit the performance of template-based APR to build comprehensive knowledge about the effectiveness of fix patterns, and to highlight the importance of complementary steps such as fault localization or donor code retrieval. To that…
Context: Learning-based automatic program repair techniques are showing promise to provide quality fix suggestions for detected bugs in the source code of the software. These tools mostly exploit historical data of buggy and fixed code…
Sequence-to-sequence models have been used to transform erroneous programs into correct ones when trained with a large enough dataset. Some recent studies also demonstrated strong empirical evidence that code review could improve the…