Related papers: EvoC2Rust: A Skeleton-guided Framework for Project…
This paper explores the use of Large Language Models (LLMs) to automate the generation of test skeletons -- structural templates that outline unit test coverage without implementing full test logic. Test skeletons are especially important…
We propose a new Verbal Reinforcement Learning (VRL) framework for interpretable task-level planning in mobile robotic systems operating under execution uncertainty. The framework follows a closed-loop architecture that enables iterative…
Dancing Links connotes an optimization to a circular doubly-linked list data structure implementation which provides for fast list element removal and restoration. The Dancing Links optimization is used primarily in fast algorithms to find…
Recent advances in multimodal large language models (MLLMs) have shown impressive reasoning capabilities. However, further enhancing existing MLLMs necessitates high-quality vision-language datasets with carefully curated task complexities,…
Large language models (LLMs) have already revolutionized code generation, after being pretrained on publicly available code data. However, while various methods have been proposed to augment LLMs with retrieved knowledge and enhance the…
CUDA kernel optimization has become a critical bottleneck for AI performance, as deep learning training and inference efficiency directly depends on highly optimized GPU kernels. Despite the promise of Large Language Models (LLMs) for…
Memory safety violations in low-level code, written in languages like C, continues to remain one of the major sources of software vulnerabilities. One method of removing such violations by construction is to port C code to a safe C dialect.…
Large language models (LLMs) are widely used for code generation, but their security reliability remains inconsistent across languages and prompting strategies. Existing prompt engineering improves functional correctness but rarely ensures…
Core to the vision-and-language navigation (VLN) challenge is building robust instruction representations and action decoding schemes, which can generalize well to previously unseen instructions and environments. In this paper, we report…
LLM-based agents depend on effective tool-use policies to solve complex tasks, yet optimizing these policies remains challenging due to delayed supervision and the difficulty of credit assignment in long-horizon trajectories. Existing…
Despite the success of large language models (LLMs) in Text-to-SQL tasks, open-source LLMs encounter challenges in contextual understanding and response coherence. To tackle these issues, we present \ours, a systematic methodology tailored…
Loop invariants are essential for proving the correctness of programs with loops. Developing loop invariants is challenging, and fully automatic synthesis cannot be guaranteed for arbitrary programs. Some approaches have been proposed to…
Large language models have recently evolved from fluent text generation to advanced reasoning across diverse domains, giving rise to reasoning language models. Among these domains, mathematical reasoning serves as a representative benchmark…
Code translation aims to convert a program from one programming language (PL) to another. This long-standing software engineering task is crucial for modernizing legacy systems, ensuring cross-platform compatibility, enhancing performance,…
LLM-driven multi-agent collaboration (MAC) systems have demonstrated impressive capabilities in automatic software development at the function level. However, their heavy reliance on human design limits their adaptability to the diverse…
Ontologies and knowledge graphs require continuous evolution to remain comprehensive and accurate, but manual curation is labor intensive. Large Language Models (LLMs) possess vast unstructured knowledge but struggle with maintaining…
Software engineering activities frequently involve edits to existing code. However, contemporary code language models (LMs) lack the ability to handle diverse types of code-edit requirements. In this work, we attempt to overcome this…
Ensuring content safety in large language models (LLMs) is essential for their deployment in real-world applications. However, existing safety guardrails are predominantly tailored for high-resource languages, leaving a significant portion…
Chain-of-thought has been proven essential for enhancing the complex reasoning abilities of Large Language Models (LLMs), but it also leads to high computational costs. Recent advances have explored the method to route queries among…
Open Source Software (OSS) has become a very important and crucial infrastructure worldwide because of the value it provides. OSS typically depends on contributions from developers across diverse backgrounds and levels of experience. Making…