代码大模型 / AI 编程 - arXivDaily 专题

2501.05899 2025-10-13 cs.SE 57%

Prompt engineering and its implications on the energy consumption of Large Language Models

Riccardo Rubei, Aicha Moussaid, Claudio di Sipio, Davide di Ruscio

专题命中代码评测：code generation(abstract)；分类 cs.SE

2508.16185 2025-10-09 cs.CL 57%

ParamBench: A Graduate-Level Benchmark for Evaluating LLM Understanding on Indic Subjects

Ayush Maheshwari, Kaushal Sharma, Vivek Patel, Aditya Maheshwari

专题命中代码评测：code generation(abstract)；分类 cs.CL

2501.05468 2025-10-09 cs.CL 57%

LatteReview: A Multi-Agent Framework for Systematic Review Automation Using Large Language Models

Pouria Rouzrokh, Bardia Khosravi, Parsa Rouzrokh, Moein Shariatnia

专题命中代码评测：repository(abstract)；分类 cs.CL

Comments 31 pages, 5 figures, 5 tables

2510.06014 2025-10-08 cs.AI 57%

ARISE: An Adaptive Resolution-Aware Metric for Test-Time Scaling Evaluation in Large Reasoning Models

Zhangyue Yin, Qiushi Sun, Zhiyuan Zeng, Zhiyuan Yu, Qipeng Guo, Xuanjing Huang, Xipeng Qiu

机构 * Fudan University（复旦大学）； The University of Hong Kong（香港大学）； Nanjing University（南京大学）； Shanghai AI Laboratory（上海人工智能实验室）； Shanghai Innovation Institute（上海创新研究院）

专题命中代码评测：code generation(abstract)；分类 cs.AI

Comments 19 pages, 7 figures

2505.19271 2025-10-08 cs.SE 57%

VerifyThisBench: Generating Code, Specifications, and Proofs All at Once

Xun Deng, Sicheng Zhong, Barış Bayazıt, Andreas Veneris, Fan Long, Xujie Si

专题命中代码评测：code generation(abstract)；分类 cs.SE

2510.04257 2025-10-07 cs.CR cs.AI 57%

AgentTypo: Adaptive Typographic Prompt Injection Attacks against Black-box Multimodal Agents

Yanjie Li, Yiming Cao, Dong Wang, Bin Xiao

机构 * Computing Department of Hong Kong Polytechnic University（香港理工大学计算机系）； Computing Department, The Hong Kong Polytechnic University（香港理工大学计算机系）

专题命中代码评测：repository(abstract)；分类 cs.AI

Comments 13 pages, 8 figures. Submitted to IEEE Transactions on Information Forensics & Security

2510.01576 2025-10-03 cs.CV cs.AI cs.HC 57%

Guiding Multimodal Large Language Models with Blind and Low Vision People Visual Questions for Proactive Visual Interpretations

Ricardo Gonzalez Penuela, Felipe Arias-Russi, Victor Capriles

专题命中代码评测：repository(abstract)；分类 cs.AI

Comments 7 pages, 2 figure, 2 tables, CV4A11y Workshop at ICCV 2025

2510.00946 2025-10-02 cs.SE 57%

ChatGPT in Introductory Programming: Counterbalanced Evaluation of Code Quality, Conceptual Learning, and Student Perceptions

Shiza Andleeb, Brandon Kantorski, Jeffrey C. Carver

专题命中代码评测：code generation(abstract)；分类 cs.SE

Comments Accepted to SIGCITE'25

2509.26111 2025-10-01 cs.SE 57%

A Multi-Language Object-Oriented Programming Benchmark for Large Language Models

Shuai Wang, Liang Ding, Li Shen, Yong Luo, Han Hu, Lefei Zhang, Fu Lin

专题命中代码评测：code generation(abstract)；分类 cs.SE

Comments 20 pages, 12 figures

2509.01245 2025-10-01 cs.AI cs.MA cs.OS 57%

Towards Agentic OS: An LLM Agent Framework for Linux Schedulers

Yusheng Zheng, Yanpeng Hu, Wei Zhang, Andi Quinn

机构 * UC Santa Cruz, CA, USA（加州大学圣克ruz分校）； University of Connecticut（康涅狄格大学）； ShanghaiTech University（上海科技大学）

专题命中代码评测：repository(abstract)；分类 cs.AI

Journal ref MLforSystem 2025

2509.20136 2025-09-25 cs.SE 57%

V-GameGym: Visual Game Generation for Code Large Language Models

Wei Zhang, Jack Yang, Renshuai Tao, Lingzheng Chai, Shawn Guo, Jiajun Wu, Xiaoming Chen, Ganqu Cui, Ning Ding, Xander Xu, Hu Wei, Bowen Zhou

专题命中代码评测：code generation(abstract)；分类 cs.SE

2507.03616 2025-09-24 cs.AI 57%

EvoAgentX: An Automated Framework for Evolving Agentic Workflows

Yingxu Wang, Siwei Liu, Jinyuan Fang, Zaiqiao Meng

机构 * Mohamed bin Zayed University of Artificial Intelligence（莫莫德·本·扎耶德人工智能大学）； University of Aberdeen（阿伯丁大学）； University of Glasgow（格拉斯哥大学）

专题命中代码评测：code generation(abstract)；分类 cs.AI

2406.14498 2025-09-23 cs.CL 57%

LLaSA: A Sensor-Aware LLM for Natural Language Reasoning of Human Activity from IMU Data

Sheikh Asif Imran, Mohammad Nur Hossain Khan, Subrata Biswas, Bashima Islam

机构 * Worcester Polytechnic Institute（沃斯特理工大学）

专题命中代码评测：repository(abstract)；分类 cs.CL

2505.14423 2025-09-23 cs.CL 57%

Scaling Low-Resource MT via Synthetic Data Generation with LLMs

Ona de Gibert, Joseph Attieh, Teemu Vahtola, Mikko Aulamo, Zihao Li, Raúl Vázquez, Tiancheng Hu, Jörg Tiedemann

机构 * University of Helsinki（赫尔辛基大学）； University of Cambridge（剑桥大学）

专题命中代码评测：repository(abstract)；分类 cs.CL

Comments Accepted at EMNLP 2025 Main Conference

2504.07002 2025-09-23 cs.CR cs.SE 57%

DeCoMa: Detecting and Purifying Code Dataset Watermarks through Dual Channel Code Abstraction

Yuan Xiao, Yuchen Chen, Shiqing Ma, Haocheng Huang, Chunrong Fang, Yanwei Chen, Weisong Sun, Yunfeng Zhu, Xiaofang Zhang, Zhenyu Chen

专题命中代码评测：code model(abstract)；分类 cs.SE

Comments Accepted to ISSTA 2025. Code is available at https://github.com/xiaoyuanpigo/DeCoMa

2406.17974 2025-09-23 cs.CL cs.CV 57%

Evaluating Fairness in Large Vision-Language Models Across Diverse Demographic Attributes and Prompts

Xuyang Wu, Yuan Wang, Hsin-Tai Wu, Zhiqiang Tao, Yi Fang

机构 * Santa Clara University（圣克拉拉大学）； DOCOMO Innovations, Inc.（DOCOMO创新公司）； Rochester Institute of Technology（罗切斯特理工学院）

专题命中代码评测：repository(abstract)；分类 cs.CL

Comments EMNLP Findings

2509.12649 2025-09-17 cs.CR cs.AI 57%

A Systematic Evaluation of Parameter-Efficient Fine-Tuning Methods for the Security of Code LLMs

Kiho Lee, Jungkon Kim, Doowon Kim, Hyoungshick Kim

机构 * Samsung Research（三星研究院）； University of Tennessee, Knoxville（田纳西大学 Knoxville分校）； Sungkyunkwan University（成均馆大学）

专题命中代码评测：code generation(abstract)；分类 cs.AI

Comments 25 pages

2503.22388 2025-09-17 cs.CL 57%

Why Stop at One Error? Benchmarking LLMs as Data Science Code Debuggers for Multi-Hop and Multi-Bug Errors

Zhiyu Yang, Shuo Wang, Yukun Yan, Yang Deng

机构 * Singapore Management University（新加坡管理大学）； Tsinghua University（清华大学）

专题命中代码评测：code generation(abstract)；分类 cs.CL

Comments Accepted at EMNLP 2025 Main, Oral

2509.10708 2025-09-16 cs.CL 57%

SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation

Iman Barati, Mostafa Amiri, Heshaam Faili

机构 * Iran University of Science and Technology（伊朗科学技术大学）； University of Tehran（塔里哈大学）

专题命中代码评测：repository(abstract)；分类 cs.CL

2507.04779 2025-09-15 stat.ML cs.LG stat.ME 57%

Constructive Universal Approximation and Sure Convergence for Multi-Layer Neural Networks

Chien-Ming Chi

机构 * Academia Sinica（中华学术院）

专题命中代码评测：repository(abstract)；分类 cs.LG

Comments 34 pages, 3 figures, 7 tables

2509.06885 2025-09-09 cs.CV cs.AI 57%

Barlow-Swin: Toward a novel siamese-based segmentation architecture using Swin-Transformers

Morteza Kiani Haftlang, Mohammadhossein Malmir, Foroutan Parand, Umberto Michelucci, Safouane El Ghazouali

机构 * HSLU, Lucerne University of Applied Sciences and Arts（卢塞恩应用科学与艺术大学）； Technical University of Munich（慕尼黑技术大学）； University College London (UCL)（伦敦大学学院）； TOELT LLC AI lab（TOELT LLC人工智能实验室）

专题命中代码评测：repository(abstract)；分类 cs.AI

2509.06024 2025-09-09 cs.AI 57%

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL

Haoyang He, Zihua Rong, Kun Ji, Chenyang Li, Qing Huang, Chong Xia, Lan Yang, Honggang Zhang

机构 * Beijing University of Posts and Telecommunications（北京邮电大学）

专题命中代码评测：repository(abstract)；分类 cs.AI

2509.03787 2025-09-05 cs.IR cs.CL 57%

Evaluating the Robustness of Retrieval-Augmented Generation to Adversarial Evidence in the Health Domain

Shakiba Amirshahi, Amin Bigdeli, Charles L. A. Clarke, Amira Ghenai

机构 * University of Waterloo（滑铁卢大学）； Toronto Metropolitan University（多伦多 Metropolitan 大学）

专题命中代码评测：repository(abstract)；分类 cs.CL

2506.18096 2025-09-04 cs.AI 57%

Deep Research Agents: A Systematic Examination And Roadmap

Yuxuan Huang, Yihang Chen, Haozheng Zhang, Kang Li, Huichi Zhou, Meng Fang, Linyi Yang, Xiaoguang Li, Lifeng Shang, Songcen Xu, Jianye Hao, Kun Shao, Jun Wang

机构 * Deep Research Agents（深度研究代理）

专题命中代码评测：repository(abstract)；分类 cs.AI

2509.02022 2025-09-03 cs.SE 57%

Scalable Thread-Safety Analysis of Java Classes with CodeQL

Bjørnar Haugstad Jåtten, Simon Boye Jørgensen, Rasmus Petersen, Raúl Pardo

专题命中代码评测：repository(abstract)；分类 cs.SE

2509.01142 2025-09-03 cs.CL 57%

Dream-Coder 7B: An Open Diffusion Language Model for Code

Zhihui Xie, Jiacheng Ye, Lin Zheng, Jiahui Gao, Jingwei Dong, Zirui Wu, Xueliang Zhao, Shansan Gong, Xin Jiang, Zhenguo Li, Lingpeng Kong

机构 * The University of Hong Kong（香港大学）； Huawei Noah’s Ark Lab（华为诺亚实验室）

专题命中代码评测：code generation(abstract)；分类 cs.CL

2502.11419 2025-09-03 cs.CL 57%

InsBank: Evolving Instruction Subset for Ongoing Alignment

Jiayi Shi, Yiwei Li, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Huan Ren, Yao Hu, Kan Li

机构 * School of Computer Science, Beijing Institute of Technology（计算机科学学院，北京理工大学）

专题命中代码评测：repository(abstract)；分类 cs.CL

2508.20141 2025-08-29 eess.IV cs.AI cs.CV 57%

UltraEar: a multicentric, large-scale database combining ultra-high-resolution computed tomography and clinical data for ear diseases

Ruowei Tang, Pengfei Zhao, Xiaoguang Li, Ning Xu, Yue Cheng, Mengshi Zhang, Zhixiang Wang, Zhengyu Zhang, Hongxia Yin, Heyu Ding, Shusheng Gong, Yuhe Liu, Zhenchang Wang

专题命中代码评测：repository(abstract)；分类 cs.AI

2508.19298 2025-08-28 cs.CV cs.AI 57%

DemoBias: An Empirical Study to Trace Demographic Biases in Vision Foundation Models

Abu Sufian, Anirudha Ghosh, Debaditya Barman, Marco Leo, Cosimo Distante

机构 * CNR-ISASI（意大利那不勒斯）； Visva-Bharati（维斯瓦-巴哈蒂）

专题命中代码评测：repository(abstract)；分类 cs.AI

Comments 6 pages, 4 figures, 13th International Workshop on Biometrics and Forensics (IWBF)

2508.18783 2025-08-27 cs.CL 57%

Controllable Conversational Theme Detection Track at DSTC 12

Igor Shalyminov, Hang Su, Jake Vincent, Siffi Singh, Jason Cai, James Gung, Raphael Shu, Saab Mansour

机构 * Amazon（亚马逊）

专题命中代码评测：repository(abstract)；分类 cs.CL

Comments DSTC12@SigDial2025; data and code available at https://github.com/amazon-science/dstc12-controllable-conversational-theme-detection

1. 代码评测 1750 篇

Prompt engineering and its implications on the energy consumption of Large Language Models

ParamBench: A Graduate-Level Benchmark for Evaluating LLM Understanding on Indic Subjects

LatteReview: A Multi-Agent Framework for Systematic Review Automation Using Large Language Models

ARISE: An Adaptive Resolution-Aware Metric for Test-Time Scaling Evaluation in Large Reasoning Models

VerifyThisBench: Generating Code, Specifications, and Proofs All at Once

AgentTypo: Adaptive Typographic Prompt Injection Attacks against Black-box Multimodal Agents

Guiding Multimodal Large Language Models with Blind and Low Vision People Visual Questions for Proactive Visual Interpretations

ChatGPT in Introductory Programming: Counterbalanced Evaluation of Code Quality, Conceptual Learning, and Student Perceptions

A Multi-Language Object-Oriented Programming Benchmark for Large Language Models

Towards Agentic OS: An LLM Agent Framework for Linux Schedulers

V-GameGym: Visual Game Generation for Code Large Language Models

EvoAgentX: An Automated Framework for Evolving Agentic Workflows

LLaSA: A Sensor-Aware LLM for Natural Language Reasoning of Human Activity from IMU Data

Scaling Low-Resource MT via Synthetic Data Generation with LLMs

DeCoMa: Detecting and Purifying Code Dataset Watermarks through Dual Channel Code Abstraction

Evaluating Fairness in Large Vision-Language Models Across Diverse Demographic Attributes and Prompts

A Systematic Evaluation of Parameter-Efficient Fine-Tuning Methods for the Security of Code LLMs

Why Stop at One Error? Benchmarking LLMs as Data Science Code Debuggers for Multi-Hop and Multi-Bug Errors

SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation

Constructive Universal Approximation and Sure Convergence for Multi-Layer Neural Networks

Barlow-Swin: Toward a novel siamese-based segmentation architecture using Swin-Transformers

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL

Evaluating the Robustness of Retrieval-Augmented Generation to Adversarial Evidence in the Health Domain

Deep Research Agents: A Systematic Examination And Roadmap

Scalable Thread-Safety Analysis of Java Classes with CodeQL

Dream-Coder 7B: An Open Diffusion Language Model for Code

InsBank: Evolving Instruction Subset for Ongoing Alignment

UltraEar: a multicentric, large-scale database combining ultra-high-resolution computed tomography and clinical data for ear diseases

DemoBias: An Empirical Study to Trace Demographic Biases in Vision Foundation Models

Controllable Conversational Theme Detection Track at DSTC 12