代码大模型 / AI 编程

Recursive Program Synthesis from Sketches and Mixed-Quantifier Properties

从混合量词属性中递归程序合成

Derek Egolf, Stavros Tripakis

专题命中 代码生成 ：program synthesis(title)

AI总结 本文提出了一种基于反例引导和预防性剪枝的递归程序合成方法，通过斯科伦化将混合量词问题转化为$\forall^*$-合成问题，提升合成效率。

Towards Transparent Checkpointing with AI-driven Code Generation

迈向基于AI驱动代码生成的透明检查点

Hai Duc Nguyen, Tekin Bicer, Kyle Chard, Ian Foster, Bogdan Nicolae

专题命中 代码生成 ：code generation(title)

AI总结 研究使用大型语言模型自动为MPI科学应用生成检查点/重启代码，平均50分钟完成，开销可忽略，恢复效率与人工实现相当。

Journal ref FlexScience'26: The 2026 Workshop on AI and Scientific Computing at Scale using Flexible Computing Infrastructures (in conjunction with HPDC'26)

False Security Confidence in Benign LLM Code Generation

良性大语言模型代码生成中的虚假安全信心

Xiaolei Ren

专题命中 代码生成 ：code generation(title)

AI总结 本文研究在无攻击场景下，功能正确但存在安全漏洞的代码生成现象，提出FSC率作为衡量指标，并定义FSC-hard作为新的评估层次。

Comments 6 pages; technical report

Relationships Between Trust, Compliance, and Performance for Novice Programmers Using AI Code Generation

使用AI代码生成的初级程序员中信任、合规性和绩效之间的关系

Nicholas Gardella, Matthew L. Bolton, Sara L. Riggs

专题命中 代码生成 ：code generation(title)

AI总结 研究探讨了初级程序员在时间压力下使用AI开发环境时，信任与编程性能及AI合规性的关系，发现性能影响信任，但信任与合规性无直接关联。

ArtiCAD: Articulated CAD Assembly Design via Multi-Agent Code Generation

ArtiCAD: 通过多智能体代码生成实现可动CAD装配设计

Yuan Shui, Yandong Guan, Zhanwei Zhang, Juncheng Hu, Jing Zhang, Dong Xu, Qian Yu

机构 * School of Software, Beihang University（北京航空航天大学软件学院） ； Zhejiang University（浙江大学） ； The University of Hong Kong（香港大学） 纠错

专题命中 代码生成 ：code generation(title)

AI总结 ArtiCAD通过多智能体系统从文本或图像生成可编辑的可动CAD装配，利用连接器定义连接点和关节参数，提升空间推理能力，通过验证步骤和回滚机制确保输出质量，验证了其在概念设计、物理原型和AI训练资产生成中的应用。

Text to Automata Diagrams: Comparing TikZ Code Generation with Direct Image Synthesis

文本到自动机图：比较TikZ代码生成与直接图像合成

Ethan Young, Zichun Wang, Aiden Taylor, Chance Jewell, Julian Myers, Satya Sri Rajiteswari Nimmagadda, Anthony White, Aniruddha Maiti, Ananya Jana

机构 * Marshall University（马歇尔大学） ； West Virginia State University（西弗吉尼亚州立大学） 纠错

专题命中 代码生成 ：code generation(title)

AI总结 本研究比较了通过视觉-语言模型生成TikZ代码与直接图像合成在生成自动机图描述中的效果，发现人工修正能显著提高生成准确性。

Comments Accepted to ASEE North Central Section 2026

HDLFORGE: A Two-Stage Multi-Agent Framework for Efficient Verilog Code Generation with Adaptive Model Escalation

HDLFORGE：一种用于高效Verilog代码生成的两阶段多智能体框架

Armin Abdollahi, Saeid Shokoufa, Negin Ashrafi, Mehdi Kamal, Massoud Pedram

专题命中 代码生成 ：code generation(title)

AI总结 HDLFORGE通过两阶段多智能体框架实现高效Verilog代码生成，通过自适应模型升级提升生成准确性与效率。

Tapas Are Free! Training-Free Adaptation of Programmatic Agents via LLM-Guided Program Synthesis in Dynamic Environments

Tapas Are Free! 通过LLM引导的程序合成实现动态环境下的免训练程序代理适应

Jinwei Hu, Yi Dong, Youcheng Sun, Xiaowei Huang

专题命中 代码生成 ：program synthesis(title)

AI总结 TAPA通过LLM引导的程序合成，在动态环境中实现免训练的程序代理适应，提升网络安全和群体智能任务的性能与可靠性。

Comments Extended version of the paper accepted at AAAI-26 Oral to comply with the AAAI camera-ready requirements with minor revisions

ScreenCoder: Advancing Visual-to-Code Generation for Front-End Automation via Modular Multimodal Agents

Yilei Jiang, Yaozhi Zheng, Yuxuan Wan, Jiaming Han, Qunzhong Wang, Michael R. Lyu, Xiangyu Yue

机构 * CUHK（香港中文大学） ； MMLab（多模态实验室） ； ARISE Lab（ARISE实验室） 纠错

专题命中 代码生成 ：code generation(title)

Comments ScreenCoder-v2

MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds

Bingquan Dai, Li Ray Luo, Qihong Tang, Jie Wang, Xinyu Lian, Hao Xu, Minghan Qin, Xudong Xu, Bo Dai, Haoqian Wang, Zhaoyang Lyu, Jiangmiao Pang

机构 * Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； Tsinghua University（清华大学） ； Harbin Institute of Technology（哈尔滨工业大学） ； Beijing Institute of Technology（北京理工大学） ； AI Thrust, HKUST(GZ)（AI thrust, 香港科技大学（广州）） 纠错

专题命中 代码生成 ：code generation(title)

GP and LLMs for Program Synthesis: No Clear Winners

Jose Guadalupe Hernandez, Anil Kumar Saini, Gabriel Ketron, Jason H. Moore

专题命中 代码生成 ：program synthesis(title)

VQ-LLM: High-performance Code Generation for Vector Quantization Augmented LLM Inference

Zihan Liu, Xinhao Luo, Junxian Guo, Wentao Ni, Yangjie Zhou, Yue Guan, Cong Guo, Weihao Cui, Yu Feng, Minyi Guo, Yuhao Zhu, Minjia Zhang, Jingwen Leng, Chen Jin

专题命中 代码生成 ：code generation(title)

Code Generation for Near-Roofline Finite Element Actions on GPUs from Symbolic Variational Forms

Kaushik Kulkarni, Andreas Klöckner

专题命中 代码生成 ：code generation(title)

Accelerating Numerical Relativity with Code Generation: CUDA-enabled Hyperbolic Relaxation

Samuel D. Tootle, Leonardo R. Werneck, Thiago Assumpção, Terrence Pierre Jacques, Zachariah B. Etienne

专题命中 代码生成 ：code generation(title)

Comments 29 pages, 6 figures, published version

Beyond Affine Loops: A Geometric Approach to Program Synthesis

Erdenebayar Bayarmagnai, Fatemeh Mohammadi, Rémi Prébet

专题命中 代码生成 ：program synthesis(title)

Automated Quantum Chemistry Code Generation with the p$^\dagger$q Package

Marcus D. Liebenthal, Stephen H. Yuwono, Lauren N. Koulias, Run R. Li, Nicholas C. Rubin, A. Eugene DePrince

专题命中 代码生成 ：code generation(title)

Design2GarmentCode: Turning Design Concepts to Tangible Garments Through Program Synthesis

Feng Zhou, Ruiyang Liu, Chen Liu, Gaofeng He, Yong-Lu Li, Xiaogang Jin, Huamin Wang

专题命中 代码生成 ：program synthesis(title)

Comments The IEEE/CVF Conference on Computer Vision and Pattern Recognition (2025)

Beyond Code Generation: LLM-supported Exploration of the Program Design Space

J. D. Zamfirescu-Pereira, Eunice Jun, Michael Terry, Qian Yang, Björn Hartmann

专题命中 代码生成 ：code generation(title)

Comments 17 pages; 4 figures; 1 table; to appear in CHI '25

Automated MPI-X code generation for scalable finite-difference solvers

George Bisbas, Rhodri Nelson, Mathias Louboutin, Fabio Luporini, Paul H. J. Kelly, Gerard Gorman

专题命中 代码生成 ：code generation(title)

Comments 11 pages, 12 figures (23 pages with References and Appendix)

Face2QR: A Unified Framework for Aesthetic, Face-Preserving, and Scannable QR Code Generation

Xuehao Cui, Guangyang Wu, Zhenghao Gan, Guangtao Zhai, Xiaohong Liu

专题命中 代码生成 ：code generation(title)

AutoFreeFem: Automatic code generation with FreeFEM++ and LaTex output for shape and topology optimization of non-linear multi-physics problems

Grégoire Allaire, Michael H. Gfrerer

专题命中 代码生成 ：code generation(title)

Code Generation and Performance Engineering for Matrix-Free Finite Element Methods on Hybrid Tetrahedral Grids

Fabian Böhm, Daniel Bauer, Nils Kohl, Christie Alappat, Dominik Thönnes, Marcus Mohr, Harald Köstler, Ulrich Rüde

专题命中 代码生成 ：code generation(title)

Comments 22 pages

Open-Universe Indoor Scene Generation using LLM Program Synthesis and Uncurated Object Databases

Rio Aguina-Kang, Maxim Gumin, Do Heon Han, Stewart Morris, Seung Jean Yoo, Aditya Ganeshan, R. Kenny Jones, Qiuhong Anna Wei, Kailiang Fu, Daniel Ritchie

专题命中 代码生成 ：program synthesis(title)

Comments See ancillary files for link to supplemental material

Text2QR: Harmonizing Aesthetic Customization and Scanning Robustness for Text-Guided QR Code Generation

Guangyang Wu, Xiaohong Liu, Jun Jia, Xuehao Cui, Guangtao Zhai

专题命中 代码生成 ：code generation(title)

Comments Accepted by CVPR 2024

Visualizing Quantum Circuit Probability -- estimating computational action for quantum program synthesis

Bao Gia Bach, Akash Kundu, Tamal Acharya, Aritra Sarkar

专题命中 代码生成 ：program synthesis(title)

Comments 17 pages

Code generation for AMReX with applications to numerical relativity

Adam J Peterson, Don Willcox, Phillip Moesta

专题命中 代码生成 ：code generation(title)

Comments 26 pages, 15 figures

FIRESTARTER 2: Dynamic Code Generation for Processor Stress Tests

Robert Schöne, Markus Schmidl, Mario Bielert, Daniel Hackenberg

专题命中 代码生成 ：code generation(title)

Comments supported in part by the German Research Foundation (DFG) within the CRC 912 - HAEC

Random Hash Code Generation for Cancelable Fingerprint Templates using Vector Permutation and Shift-order Process

Sani M. Abdullahi, Sun Shuifa

专题命中 代码生成 ：code generation(title)

Comments 10 pages, 5 figures

Semi-Automated Protocol Disambiguation and Code Generation

Jane Yen, Tamás Lévai, Qinyuan Ye, Xiang Ren, Ramesh Govindan, Barath Raghavan

专题命中 代码生成 ：code generation(title)

Cain: Automatic Code Generation for Simultaneous Convolutional Kernels on Focal-plane Sensor-processors

Edward Stow, Riku Murai, Sajad Saeedi, Paul H. J. Kelly

专题命中 代码生成 ：code generation(title)

Comments 17 pages, 4 figures, Accepted at LCPC 2020 to be published by Springer