Related papers: RepoST: Scalable Repository-Level Coding Environme…

In this work, we study the problem of code generation with a large language model (LLM), with a focus on generating SQL queries from natural language questions. We ask: Instead of using supervised fine tuning with text-code pairs, can we…

Reservoir Computing is an Unconventional Computation model to perform computation on various different substrates, such as recurrent neural networks or physical materials. The method takes a 'black-box' approach, training only the outputs…

Traditional benchmarks for large language models (LLMs), such as HELM and AIR-BENCH, primarily assess safety through breadth-oriented evaluation across diverse tasks and risk categories. However, real-world deployment often exposes a…

Reinforcement learning (RL) offers a capable and intuitive structure for the fundamental sequential decision-making problem. Despite impressive breakthroughs, it can still be difficult to employ RL in practice in many simple applications.…

Learning in the combinatorially large output space of sequence generation problems is challenging as providing expert demonstrations scales poorly with sequence length, and RL struggles with sparse rewards. Between dense demonstrations in…

Large language models (LLMs) have achieved strong performance on code generation, but existing methods still struggle with repository-level code generation under executable validation. Under this evaluation setting, success is determined…

Recruiting and onboarding software testing professionals are complex and cost intensive activities. Whether onboarding is successful and sustainable depends on both the employee as well as the organization and is influenced by a number of…

Reinforcement learning (RL) has become a key paradigm for training software engineering (SWE) agents, but existing pipelines typically rely on per-task containers for isolation. At scale, pre-built container images incur substantial storage…

LLM-based code agents treat repositories as unstructured text, applying edits through brittle string matching that frequently fails due to formatting drift or ambiguous patterns. We propose reframing the codebase as a structured action…

Increased reproducibility of machine learning research has been a driving force for dramatic improvements in learning performances. The scientific community further fosters this effort by including reproducibility ratings in reviewer forms…

Testing plays a crucial role in the software development cycle, enabling the detection of bugs, vulnerabilities, and other undesirable behaviors. To perform software testing, testers need to write code snippets that execute the program…

Ensuring safety in robotic systems remains a fundamental challenge, especially when deploying offline policy-learning methods such as imitation learning in dynamic environments. Traditional behavior cloning (BC) often fails to generalize…

Reinforcement Learning (RL) is an important paradigm for aligning Diffusion Language Models (DLMs) toward functional correctness in code generation. However, these models often encounter a ``capability cliff'' on complex tasks, where…

We explore a method for improving the performance of large language models through self-reflection and reinforcement learning. By incentivizing the model to generate better self-reflections when it answers incorrectly, we demonstrate that a…

Reinforcement learning (RL) has become a powerful approach for improving the reasoning capabilities of large language models (LLMs), as evidenced by recent successes such as OpenAI's o1 and Deepseek-R1. However, applying RL at scale remains…

Traditional benchmarks for large language models (LLMs), such as HELM and AIR-BENCH, primarily assess safety risk through breadth-oriented evaluation across diverse tasks. However, real-world deployment often exposes a different class of…

The personalization of black-box large language models (LLMs) is a critical yet challenging task. Existing approaches predominantly rely on context injection, where user history is embedded into the prompt to directly guide the generation…

While large language models (LLMs) are powerful assistants in programming tasks, they may also produce malicious code. Testing LLM-generated code therefore poses significant risks to assessment infrastructure tasked with executing untrusted…

The instruction-following ability of Large Language Models (LLMs) has cultivated a class of LLM-based systems capable of approaching complex tasks such as making edits to large code repositories. Due to the high sensitivity and…

While large language model agents have advanced software engineering tasks, the unscalable nature of existing test-based supervision is limiting the potential improvement of data scaling. The reason is twofold: (1) building and running test…