Related papers: RLocator: Reinforcement Learning for Bug Localizat…

Automated Program Repair (APR) has benefited from the code understanding and generation capabilities of Large Language Models (LLMs). Existing feedback-based APR methods iteratively refine candidate patches using test execution feedback and…

Recently, Large Language Model (LLM)-empowered recommender systems have revolutionized personalized recommendation frameworks and attracted extensive attention. Despite the remarkable success, existing LLM-empowered RecSys have been…

The growing disparity between the exponential scaling of computational resources and the finite growth of high-quality text data now constrains conventional scaling approaches for large language models (LLMs). To address this challenge, we…

Large language model (LLM) coding agents increasingly operate over repositories, terminals, tests, and execution traces across long software-engineering episodes. Persistent memory is useful, but static vector stores or generic…

Large language models (LLMs) have achieved decent results on automated program repair (APR). However, the next token prediction training objective of decoder-only LLMs (e.g., GPT-4) is misaligned with the masked span prediction objective of…

Reinforcement learning (RL) has become a cornerstone for enhancing the reasoning capabilities of large language models (LLMs), with recent innovations such as Group Relative Policy Optimization (GRPO) demonstrating exceptional…

Debugging is difficult. Recent studies show that automatic bug localization techniques have limited usefulness. One of the reasons is that programmers typically have to understand why the program fails before fixing it. In this work, we aim…

Static bug analyzers play a crucial role in ensuring software quality. However, existing analyzers for bug detection in large codebases often suffer from high false positive rates. This is primarily due to the limited capabilities of…

Combinatorial optimization (CO) is fundamental to several real-world applications, from logistics and scheduling to hardware design and resource allocation. Deep reinforcement learning (RL) has recently shown significant benefits in solving…

Learning-to-Rank (LTR) is a supervised machine learning approach that constructs models specifically designed to order a set of items or documents based on their relevance or importance to a given query or context. Despite significant…

As modern microservice systems grow increasingly popular and complex-often consisting of hundreds or even thousands of fine-grained, interdependent components-they are becoming more susceptible to frequent and subtle failures. Ensuring…

Existing web-scale recommendation systems commonly use supervised learning methods that prioritize immediate user feedback. Although reinforcement learning (RL) offers a solution to optimize longer-term goals, such as in-session engagement,…

Reinforcement learning (RL) has become a prevailing approach for fine-tuning large language models (LLMs) on complex reasoning tasks. Among recent methods, GRPO stands out for its empirical success in training models such as DeepSeek-R1,…

Data quality or data evaluation is sometimes a task as important as collecting a large volume of data when it comes to generating accurate artificial intelligence models. In fact, being able to evaluate the data can lead to a larger…

We propose an automated approach to bug assignment to developers in large open-source software projects. This way, we assist human bug triagers who are in charge of finding the best developer with the right level of expertise in a…

Watermarking has emerged as a promising solution for tracing and authenticating text generated by large language models (LLMs). A common approach to LLM watermarking is to construct a green/red token list and assign higher or lower…

Open source software (OSS) is integral to modern product development, and any vulnerability within it potentially compromises numerous products. While developers strive to apply security patches, pinpointing these patches among extensive…

Automated Program Repair (APR) agents leverage Large Language Models (LLMs) to autonomously diagnose and fix software bugs through reasoning, planning, and tool use. Despite impressive leaderboard gains on benchmarks such as SWE-bench,…

Bug fixing is generally a manually-intensive task. However, recent work has proposed the idea of automated program repair, which aims to repair (at least a subset of) bugs in different ways such as code mutation, etc. Following in the same…

Learning from human feedback has been shown to improve text-to-image models. These techniques first learn a reward function that captures what humans care about in the task and then improve the models based on the learned reward function.…