代码大模型 / AI 编程

Rethinking the Evaluation of Secure Code Generation

Shih-Chieh Dai, Jun Xu, Guanhong Tao

机构 * University of Utah（犹他大学） 纠错

专题命中 代码生成 ：code generation(title,abstract)；分类 cs.SE、cs.LG

Comments Accepted by ICSE 2026

Evaluating Software Process Models for Multi-Agent Class-Level Code Generation

Wasique Islam Shafin, Md Nakhla Rafi, Zhenhao Li, Tse-Hsun Chen

专题命中 代码生成 ：code generation(title,abstract)；分类 cs.SE

Why Do Open-Source LLMs Struggle with Data Analysis? A Systematic Empirical Study

Yuqi Zhu, Yi Zhong, Jintian Zhang, Ziheng Zhang, Shuofei Qiao, Yujie Luo, Lun Du, Da Zheng, Ningyu Zhang, Huajun Chen

专题命中 代码生成 ：code generation(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments AAAI 2026 (oral)

HierRouter: Coordinated Routing of Specialized Large Language Models via Reinforcement Learning

Nikunj Gupta, Bill Guo, Rajgopal Kannan, Viktor K. Prasanna

机构 * David S. Hippocampus Department of Computer Science Cranberry-Lemon University（Cranberry-Lemon大学计算机科学系） ； University of Southern California（南加州大学） ； DEVCOM Army Research Office（陆军研究办公室） 纠错

专题命中 代码生成 ：code generation(abstract)；分类 cs.CL、cs.LG

EnchTable: Unified Safety Alignment Transfer in Fine-tuned Large Language Models

Jialin Wu, Kecen Li, Zhicong Huang, Xinfeng Li, Xiaofeng Wang, Cheng Hong

机构 * Ant Group（蚂蚁集团） ； Nanyang Technological University（南洋理工大学） 纠错

专题命中 代码生成 ：code generation(abstract)；分类 cs.CL

Comments Accepted by IEEE Symposium on Security and Privacy (S&P) 2026

SlideBot: A Multi-Agent Framework for Generating Informative, Reliable, Multi-Modal Presentations

Eric Xie, Danielle Waterfield, Michael Kennedy, Aidong Zhang

专题命中 代码生成 ：code generation(abstract)；分类 cs.AI

Comments 32 pages, 14 figures, accepted into EAAI 2026

The Configuration Wall: Characterization and Elimination of Accelerator Configuration Overhead

Josse Van Delm, Anton Lydike, Joren Dumoulin, Jonas Crols, Xiaoling Yi, Ryan Antonio, Jackson Woodruff, Tobias Grosser, Marian Verhelst

专题命中 代码生成 ：code generation(abstract)

Comments To appear in Proceedings of ASPLOS 2026

Diversity Over Scale: Whole-Slide Image Variety Enables H&E Foundation Model Training with Fewer Patches

Christoph Bosch, John K. L. Wong, Martin Paulikat, Myroslav Zapukhlyak, Bharti Arora, Manasi Aichmüller-Ratnaparkhe, Jens Baumann, Shivani Karn, Rutuja Kamble, Swapnil Karnik, Bhushan Khedkar, Serey Vathana Chhut, Witali Aswolinskiy, Christian Aichmüller

专题命中 程序修复 ：repository(abstract)

EnvTrace: Simulation-Based Semantic Evaluation of LLM Code via Execution Trace Alignment -- Demonstrated at Synchrotron Beamlines

Noah van der Vleuten, Anthony Flores, Shray Mathur, Max Rakitin, Thomas Hopkins, Kevin G. Yager, Esther H. R. Tsai

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

FHIR-AgentBench: Benchmarking LLM Agents for Realistic Interoperable EHR Question Answering

Gyubok Lee, Elea Bach, Eric Yang, Tom Pollard, Alistair Johnson, Edward Choi, Yugang jia, Jong Ha Lee

机构 * Korea Advanced Institute of Science & Technology（韩国科学技术院） ； Verily Life Sciences（Verily 生物科技） ； Massachusetts Institute of Technology（麻省理工学院） 纠错

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

Comments ML4H 2025 Proceedings

How Small Can You Go? Compact Language Models for On-Device Critical Error Detection in Machine Translation

Muskaan Chopra, Lorenz Sparrenberg, Sarthak Khanna, Rafet Sifa

机构 * Fraunhofer IAIS - Department of Media Engineering（弗劳恩霍夫人工智能研究所-媒体工程部门） ； University of Bonn - Department of Computer Science（波恩大学-计算机科学系） ； Lamarr Institute for Machine Learning（拉马尔人工智能与机器学习研究所） 纠错

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

Comments Accepted in IEEE BigData 2025

Efficient Hyperdimensional Computing with Modular Composite Representations

Marco Angioli, Christopher J. Kymn, Antonello Rosato, Amy Loutfi, Mauro Olivieri, Denis Kleyko

机构 * Sapienza University of Rome（罗马萨皮恩扎大学） ； University of California at Berkeley（加州大学伯克利分校） ； Örebro University（欧雷布罗大学） ； Linköping University（林哈姆斯大学） ； RISE Research Institutes of Sweden（瑞典RISE研究所） 纠错

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

Maximizing Efficiency of Dataset Compression for Machine Learning Potentials With Information Theory

Benjamin Yu, Vincenzo Lordi, Daniel Schwalbe-Koda

机构 * Department of Materials Science and Engineering, University of California, Los Angeles, CA, United States（加州大学洛杉矶分校材料科学与工程系） ； Materials Science Division, Lawrence Livermore National Laboratory, CA, United States（劳伦斯利弗莫尔国家实验室材料科学部） 纠错

专题命中 仓库级理解 ：repository(abstract)；分类 cs.LG

Comments main text + SI; code at https://github.com/dskoda/quests

From Euler to Today: Universal Mathematical Fallibility A Large-Scale Computational Analysis of Errors in ArXiv Papers

Igor Rivin

机构 * Department of Mathematics, Temple University（特拉华大学数学系） 纠错

专题命中 仓库级理解 ：repository(abstract)；分类 cs.AI

Dual-Mode Deep Anomaly Detection for Medical Manufacturing: Structural Similarity and Feature Distance

Julio Zanon Diaz, Georgios Siogkas, Peter Corcoran

专题命中 仓库级理解 ：repository(abstract)；分类 cs.AI

Comments 12 pages, 3 figures, 3 tables

Analyzing Exoplanet Transits Observed with the WFC3/UVIS G280 Grism

Munazza K. Alam, Frederick Dauphin, Amanda Pagul

专题命中 仓库级理解 ：repository(abstract)

Comments 11 pages, 8 figures, published in April 2025