Related papers: Towards Robust Agentic CUDA Kernel Benchmarking, V…

Automated kernel design is critical for overcoming software ecosystem barriers in emerging hardware platforms like RISC-V. While large language models (LLMs) have shown promise for automated kernel optimization, demonstrating success in…

Large language models (LLMs) demonstrate strong potential as agents for tool invocation due to their advanced comprehension and planning capabilities. Users increasingly rely on LLM-based agents to solve complex missions through iterative…

LLM-based reasoning models have enabled the development of agentic systems that act as co-scientists, assisting in multi-step scientific analysis. However, evaluating these systems is challenging, as it requires realistic, end-to-end…

Recently, Large Language Models (LLMs) have demonstrated significant potential in automating software engineering tasks. Generating software architecture designs from requirement documents is a crucial step in software development. However,…

The emergence of Large Language Models (LLMs) has catalyzed a paradigm shift in programming, giving rise to "vibe coding", where users can build complete projects and even control computers using natural language instructions. This paradigm…

The development of LLM-based autonomous agents for end-to-end software development represents a significant paradigm shift in software engineering. However, the scientific evaluation of these systems is hampered by significant challenges,…

LLM agents now perform strongly in software engineering, deep research, GUI automation, and various other applications, while recent agent scaffolds and models are increasingly integrating these capabilities into unified systems. Yet, most…

GPU kernel generation by LLMs has recently experienced rapid development, leveraging test-time scaling and reinforcement learning techniques. However, a key challenge for kernel generation is the scarcity of high-quality data, as most…

The evaluation of Large Language Models (LLMs) for code generation relies heavily on the quality and robustness of test cases. However, existing benchmarks often lack coverage for subtle corner cases, allowing incorrect solutions to pass.…

To meet the ever-increasing demand for computational efficiency, Neural Processing Units (NPUs) have become critical in modern AI infrastructure. However, unlocking their full potential requires developing high-performance compute kernels…

Automating the conversion of UI images into web code is a critical task for front-end development and rapid prototyping. Advances in multimodal large language models (MLLMs) have made WebUI-to-Code increasingly feasible, yet existing…

Making deep learning recommendation model (DLRM) training and inference fast and efficient is important. However, this presents three key system challenges - model architecture diversity, kernel primitive diversity, and hardware generation…

Large language model-based agents show promise for software engineering, but environment configuration remains a bottleneck due to heavy manual effort and scarce large-scale, high-quality datasets. Existing benchmarks assess only end-to-end…

Developing efficient GPU kernels is essential for scaling modern AI systems, yet it remains a complex task due to intricate hardware architectures and the need for specialized optimization expertise. Although Large Language Models (LLMs)…

Debugging CUDA programs has long been challenging because failures often arise from subtle interactions among hardware behavior, compiler decisions, memory hierarchy, and asynchronous execution. More importantly, with the rapid expansion of…

Graphic Processing Units (GPUs) have become ubiquitous in scientific computing. However, writing efficient GPU kernels can be challenging due to the need for careful code tuning. To automatically explore the kernel optimization space,…

Large Language Models (LLMs) have made significant strides in front-end code generation. However, existing benchmarks exhibit several critical limitations: many tasks are overly simplistic, test cases often lack rigor, and end-to-end…

Formal specification is essential for rigorous program verification, yet writing correct specifications remains costly and difficult to automate. Although large language models (LLMs) and agents have shown promising progress, their true…

Formal verification is the next frontier for ensuring the correctness of code generated by Large Language Models (LLMs). While methods that co-generate code and formal specifications in formal languages, like Dafny, can, in principle, prove…

The increasing agentic capabilities of Large Language Models (LLMs) have enabled their deployment in real-world applications, such as cloud services, where customer-assistant interactions exhibit high technical complexity and long-horizon…