English
Related papers

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

200 papers

The ability of Large Language Models (LLMs) to use external tools unlocks powerful real-world interactions, making rigorous evaluation essential. However, current benchmarks primarily report final accuracy, revealing what models can do but…

Computation and Language · Computer Science 2026-01-29 Qihao Wang , Yue Hu , Mingzhe Lu , Jiayue Wu , Yanbing Liu , Yuanmin Tang

Beyond scratch coding, exploiting large-scale code repositories (e.g., GitHub) for practical tasks is vital in real-world software development, yet current benchmarks rarely evaluate code agents in such authentic, workflow-driven scenarios.…

We present a comprehensive study of the commute time kernel method via the effective resistance framework analyzing the quantum complexity of the originally classical approach. Our study reveals that while there is a trade-off between…

Quantum Physics · Physics 2026-01-06 Adam Wesołowski , Karim Essafi

Large language models (LLMs) such as GPT-5 and Gemini 3 have pushed the frontier of automated reasoning and code generation. Yet current benchmarks emphasize accuracy and output quality, neglecting a critical dimension: efficiency of token…

Computation and Language · Computer Science 2026-02-25 Zheng Du , Hao Kang , Song Han , Tushar Krishna , Ligeng Zhu

Autotuning of performance-relevant source-code parameters allows to automatically tune applications without hard coding optimizations and thus helps with keeping the performance portable. In this paper, we introduce a benchmark set of ten…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-03-02 Filip Petrovič , David Střelák , Jana Hozzová , Jaroslav Oľha , Richard Trembecký , Siegfried Benkner , Jiří Filipovič

The performance of modern AI systems is fundamentally constrained by the quality of their underlying kernels, which translate high-level algorithmic semantics into low-level hardware operations. Achieving near-optimal kernels requires…

Linux kernel tuning is essential for optimizing operating system (OS) performance. However, existing methods often face challenges in terms of efficiency, scalability, and generalization. This paper introduces OS-R1, an agentic Linux kernel…

Machine Learning · Computer Science 2025-08-19 Hongyu Lin , Yuchen Li , Haoran Luo , Kaichun Yao , Libo Zhang , Mingjie Xing , Yanjun Wu

Large language models show promise for automated CUDA programming, however even the strongest coding models (e.g., Claude-Opus-4.6) may still fall short of expert-level, architecture-aware optimization. We introduce CUDAHercules, a…

Machine Learning · Computer Science 2026-05-12 Shiyang Li , Zijian Zhang , Guangyan Sun , Yuebo Luo , Winson Chen , Yanzhi Wang , Mingyi Hong , Caiwen Ding

Education is one of the most promising real-world applications for Large Language Models (LLMs). However, current LLMs rely on static pre-training knowledge and lack adaptation to individual learners, while existing RAG systems fall short…

Computers and Society · Computer Science 2026-05-12 Bingxi Zhao , Jiahao Zhang , Xubin Ren , Zirui Guo , Tianzhe Chu , Yi Ma , Chao Huang

Generating high-performance CUDA kernels remains challenging due to the need to navigate a combinatorial space of low-level transformations under noisy and expensive hardware feedback. Although large language models can synthesize…

Machine Learning · Computer Science 2026-02-16 Arijit Bhattacharjee , Heng Ping , Son Vu Le , Paul Bogdan , Nesreen K. Ahmed , Ali Jannesari

Large language models (LLMs) and agentic systems have recently demonstrated potential for automating scientific workflows, including atomistic simulations. However, their deployment in high-performance computing (HPC) environments remains…

Computational Physics · Physics 2026-04-27 William Dawson , Louis Beal , Yoann Curé , Giuseppe Fisicaro , Dorian Rolland , Luigi Genovese

The progress of humanity is driven by those successful discoveries accompanied by countless failed experiments. Researchers often seek the potential research directions by reading and then verifying them through experiments. The process…

Artificial Intelligence · Computer Science 2024-07-31 Haotian Chen , Xinjie Shen , Zeqi Ye , Wenjun Feng , Haoxue Wang , Xiao Yang , Xu Yang , Weiqing Liu , Jiang Bian

Modern software development demands code that is maintainable, testable, and scalable by organizing the implementation into modular components with iterative reuse of existing codes. We formalize this iterative, multi-turn paradigm as…

Software Engineering · Computer Science 2026-04-16 Sizhe Wang , Zhengren Wang , Dongsheng Ma , Yongan Yu , Rui Ling , Zhiyu Li , Feiyu Xiong , Wentao Zhang

The advances made by Large Language Models (LLMs) have led to the pursuit of LLM agents that can solve intricate, multi-step reasoning tasks. As with any research pursuit, benchmarking and evaluation are key corner stones to efficient and…

Artificial Intelligence · Computer Science 2024-04-10 Luca Gioacchini , Giuseppe Siracusano , Davide Sanvito , Kiril Gashteovski , David Friede , Roberto Bifulco , Carolin Lawrence

Recent advances in large language models have improved code generation, but their use in hardware description languages is still limited. Moreover, training data and testbenches for these models are often scarce. This paper presents a…

Hardware Architecture · Computer Science 2026-04-20 Mu-Chi Chen , Po-Hsuan Huang , Yu-Hung Kao , Yen-Fu Liu , Yu-Kai Hung , Cheng Liang , Shao-Chun Ho , Chia-Heng Tu , Shih-Hao Hung

We introduce a comprehensive validation framework for LLM-based agentic systems that provides systematic diagnosis and improvement of reliability failures. The framework includes fifteen failure-detection tools and two root-cause analysis…

Artificial Intelligence · Computer Science 2026-04-01 Hadar Mulian , Sergey Zeltyn , Ido Levy , Liane Galanti , Avi Yaeli , Segev Shlomov

Code completion, a key downstream task in code generation, is one of the most frequent and impactful methods for enhancing developer productivity in software development. As intelligent completion tools evolve, we need a robust evaluation…

Software Engineering · Computer Science 2024-10-25 Zhenyu Pan , Rongyu Cao , Yongchang Cao , Yingwei Ma , Binhua Li , Fei Huang , Han Liu , Yongbin Li

Large Language Models (LLMs) have emerged as powerful tools for accelerating scientific discovery, yet their static knowledge and hallucination issues hinder autonomous research applications. Recent advances integrate LLMs into agentic…

Artificial Intelligence · Computer Science 2025-12-23 Zeyu Xia , Jinzhe Ma , Congjie Zheng , Shufei Zhang , Yuqiang Li , Hang Su , P. Hu , Changshui Zhang , Xingao Gong , Wanli Ouyang , Lei Bai , Dongzhan Zhou , Mao Su

Post-training compression reduces the computational and memory costs of large language models (LLMs), enabling resource-efficient deployment. However, existing compression benchmarks only focus on language modeling (e.g., perplexity) and…

Machine Learning · Computer Science 2025-06-03 Peijie Dong , Zhenheng Tang , Xiang Liu , Lujun Li , Xiaowen Chu , Bo Li

The rapid evolution and use of Large Language Models (LLMs) in professional workflows require an evaluation of their domain-specific knowledge against industry standards. We introduceCyberCertBench, a new suite of Multiple Choice Question…

Cryptography and Security · Computer Science 2026-04-23 Gustav Keppler , Ghada Elbez , Veit Hagenmeyer