代码大模型 / AI 编程

Scalability and Optimization Strategies for GPU Enhanced Neural Networks (GeNN)

Naresh Balaji, Esin Yavuz, Thomas Nowotny

专题命中 代码生成 ：code generation(abstract)

Lighthouse: A User-Centered Web Service for Linear Algebra Software

Boyana Norris, Sa-Lin Bernstein, Ramya Nair, Elizabeth Jessup

专题命中 代码生成 ：code generation(abstract)

Comments 10 pages, 10 figures, 3 tables

An Integrated Programming and Development Environment for Adiabatic Quantum Optimization

Travis S. Humble, Alex J. McCaskey, Ryan S. Bennink, Jay J. Billings, Ed F. D'Azevedo, Blair D. Sullivan, Christine F. Klymko, Hadayat Seddiqi

专题命中 代码生成 ：program synthesis(abstract)

Comments 28 pages, 17 figures, feedback welcomed, even if it's criticism; v2 manuscript updated based on reviewer feedback; v3 manuscript updated based on reviewer feedback, title modified

Journal ref Comput. Sci. Disc. 7 015006 (2014)

An Algebraic Framework for the Real-Time Solution of Inverse Problems on Embedded Systems

Christoph Gugg, Matthew Harker, Paul O'Leary, Gerhard Rath

专题命中 代码生成 ：code generation(abstract)

Comments 24 pages, journal article

(Quantified) Horn Constraint Solving for Program Verification and Synthesis

Andrey Rybalchenko

专题命中 代码生成 ：program synthesis(abstract)

Applications of the Gauss-Jordan algorithm, done right

Jesús Aransay, Jose Divasón

专题命中 代码生成 ：code generation(abstract)

Synthesis for Polynomial Lasso Programs

Jan Leike, Ashish Tiwari

专题命中 代码生成 ：program synthesis(abstract)

Comments Paper at VMCAI'14, including appendix

High-level programming and control for industrial robotics: using a hand-held accelerometer-based input device for gesture and posture recognition

Pedro Neto, Norberto Pires, Paulo Moreira

专题命中 代码生成 ：code generation(abstract)

Comments Industrial Robot: An International Journal

Journal ref Industrial Robot: An International Journal, Vol. 37 Iss: 2, 2010, pp.137 - 147

Performance and Optimization Abstractions for Large Scale Heterogeneous Systems in the Cactus/Chemora Framework

Erik Schnetter

专题命中 代码生成 ：code generation(abstract)

Synthesis from Knowledge-Based Specifications

Ron van der Meyden, Moshe Y. Vardi

专题命中 代码生成 ：program synthesis(abstract)

Comments An extended abstract of this paper appeared in CONCUR'98

Tenth-Order Lepton Anomalous Magnetic Moment -- Sixth-Order Vertices Containing Vacuum-Polarization Subdiagrams

Tatsumi Aoyama, Masashi Hayakawa, Toichiro Kinoshita, Makiko Nio

专题命中 代码生成 ：code generation(abstract)

Comments 31 pages, 4 figures

A framework for automated PDE-constrained optimisation

S. W. Funke, P. E. Farrell

专题命中 代码生成 ：code generation(abstract)

Multilayer Perceptron Guided Key Generation Through Mutation with Recursive Replacement in Wireless Communication (MLPKG)

Arindam Sarkar, J. K. Mandal

专题命中 代码生成 ：code generation(abstract)

Comments 18 pages

Journal ref International Journal on AdHoc Networking Systems (IJANS) Vol. 2, No. 3, July 2012, 11-28

Mppsocgen: A framework for automatic generation of mppsoc architecture

Emna Kallel, Yassine Aoudni, Mouna Baklouti, Mohamed Abid

专题命中 代码生成 ：code generation(abstract)

Comments 16 pages; International Journal of Computer Science & Information Technology (IJCSIT) Vol 4, No 2, April 2012

Towards Quality of Service and Resource Aware Robotic Systems through Model-Driven Software Development

Andreas Steck, Christian Schlegel

专题命中 代码生成 ：code generation(abstract)

Comments 6 pages; 1st International Workshop on Domain-Specific Languages and models for ROBotic systems (DSLRob'10), October 2010

Local Strategy Improvement for Parity Game Solving

Oliver Friedmann, Martin Lange

专题命中 代码生成 ：program synthesis(abstract)

Journal ref EPTCS 25, 2010, pp. 118-131

Beyond XSPEC: Towards Highly Configurable Analysis

Michael S. Noble, Michael A. Nowak

专题命中 代码生成 ：code generation(abstract)

Comments Accepted by PASP, for July 2008 (15 pages)

Automatic generation of vacuum amplitude many-body perturbation series

P. D. Stevenson

专题命中 代码生成 ：code generation(abstract)

Comments Accepted for publication in Int. J. Mod. Phys. C

The Role of Schema Matching in Large Enterprises

Ken Smith, Michael Morse, Peter Mork, Maya Li, Arnon Rosenthal, David Allen, Len Seligman, Chris Wolf

专题命中 代码生成 ：code generation(abstract)

Comments CIDR 2009

FTOS-Verify: Analysis and Verification of Non-Functional Properties for Fault-Tolerant Systems

Chih-Hong Cheng, Christian Buckl, Javier Esparza, Alois Knoll

专题命中 代码生成 ：code generation(abstract)

Comments (bibliography update)

Computer Algebra Applications for Numerical Relativity

Sascha Husa, Christiane Lechner

专题命中 代码生成 ：code generation(abstract)

Comments 5 pages, no figures. To appear in the Proceedings of the Spanish Relativity Meeting (ERE 2002), Mao, Menorca, Spain, 22-24 Sept 2002

A Parallel Algorithm for Dilated Contour Extraction from Bilevel Images

B. R. Schlei, L. Prasad

专题命中 代码生成 ：code generation(abstract)

Comments 5 pages, including 3 figures. For additional detail check http://www.nis.lanl.gov/~bschlei/labvis/index.html

A Unified Issue Resolution Benchmark for Requirement Clarification, Planning, and Code Generation for Coding Agents

面向编码智能体的需求澄清、规划与代码生成的统一问题解决基准

Xin Zhou, Chun Yong Chong, Kisub Kim, Yun Peng, Rui Shu, Zihan Wu, Xu Han, Guowen Yuan, Zeyang Zhuang, Jounghoon Kim, Jeongjin Ju, Seongmin Ju, Taein Yoon, David Lo

专题命中 软件智能体 ：code generation(title,abstract)；coding agent(title,abstract)；repository(abstract)；分类 cs.SE、cs.AI

AI总结 该研究推出SWE-RPG编码智能体基准，评估发现主流编码智能体在该基准上平均解决率仅31.5%，隐性需求恢复是主要瓶颈，为改进编码智能体提供了方向。

Comments 9 pages

NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents

NL2Repo-Bench: 向编码代理的长周期仓库生成评估迈进

Jingzhe Ding, Shengda Long, Changxin Pu, Huan Zhou, Hongwan Gao, Xiang Gao, Chao He, Yue Hou, Fei Hu, Zhaojian Li, Weiran Shi, Zaiyuan Wang, Daoguang Zan, Chenchen Zhang, Xiaoxu Zhang, Qizhi Chen, Xianfu Cheng, Bo Deng, Qingshui Gu, Kai Hua, Juntao Lin, Pai Liu, Mingchen Li, Xuanguang Pan, Zifan Peng, Yujia Qin, Yong Shan, Zhewen Tan, Weihao Xie, Zihan Wang, Yishuo Yuan, Jiayu Zhang, Enduo Zhao, Yunfei Zhao, He Zhu, Liya Zhu, Chenyang Zou, Ming Ding, Jianpeng Jiao, Jiaheng Liu, Minghao Liu, Qian Liu, Chongyang Tao, Jian Yang, Tong Yang, Zhaoxiang Zhang, Xinjie Chen, Wenhao Huang, Ge Zhang

机构 * Nanjing University（南京大学） ； Peking University（北京大学） ； Beijing University of Posts and Telecommunications（北京邮电大学） ； Beihang University（北航） 纠错

专题命中 软件智能体 ：repository(title,abstract)；coding agent(title,abstract)；code generation(abstract)；分类 cs.CL

AI总结 NL2Repo-Bench通过评估编码代理在长周期内生成仓库的能力，揭示了自主软件开发中的核心挑战。

Change2Task: From Repository Changes to Executable Coding Agent Tasks and Environments

Change2Task：从仓库变更到可执行编码智能体任务与环境

Haomin Qi, Xingliang Wang, Xuanqi Gao, Baihui Sang, Xin Zhang, Minghua Ma, Pengfei Gao, Yu Kang, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang

专题命中 软件智能体 ：repository(title,abstract)；coding agent(title,abstract)；分类 cs.SE、cs.CL、cs.LG

AI总结 Change2Task系统基于仓库历史将已合并拉取请求转为编码智能体任务，在5类任务中实现79.6%验证成功率，比基准多恢复29.2%任务，可减少流程支出10.8%。

Comments 15 pages, 7 figures, and 15 tables, including appendices

Agent Retrieval Bench: Evaluating Repository Context Retrieval for Coding Agents

智能体检索基准：评估代码智能体的仓库上下文检索

Bowen Qin, Yi Xie

专题命中 软件智能体 ：repository(title,abstract)；coding agent(title,abstract)；分类 cs.CL、cs.AI

AI总结 研究代码智能体仓库上下文检索问题，引入智能体检索基准，涵盖多种检索任务和样本。评估多种检索方法，发现无单一方法占优，存在校准差距，且记录轨迹有缺失。通过试验表明检索得出的初始上下文有优势，神谕金上下文还有提升空间。

Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?

评估 AGENTS.md：仓库级上下文文件对编码助手有帮助吗？

Thibaud Gloaguen, Niels Mündler, Mark Müller, Veselin Raychev, Martin Vechev

机构 * Department of Computer Science（计算机科学系） ； ETH Zurich（苏黎世联邦理工学院） 纠错

专题命中 软件智能体 ：repository(title,abstract)；coding agent(title,abstract)；分类 cs.SE、cs.AI

AI总结 通过SWE-bench任务和开发者提交的上下文文件，评估发现上下文文件并未普遍提升编码助手的任务成功率，反而平均增加20%以上的推理成本。

Probe-and-Refine Tuning of Repository Guidance for Coding Agents

代码代理的仓库指导的探测与精炼调优

Asa Shepard, Jeannie Albrecht

机构 * Williams College（威廉姆斯学院） 纠错

专题命中 软件智能体 ：repository(title,abstract)；coding agent(title,abstract)；分类 cs.SE、cs.LG

AI总结 提出探测与精炼调优方法，通过合成bug修复探测迭代诊断和修补仓库指导文件，在SWE-bench Verified上以Qwen3.5-35B-A3B模型达到33.0%解决率，优于静态知识库的28.3%和无指导基线的25.5%。

Can Coding Agents Solve Repository-Level Issues with Rendered Code? An Exploratory Study of Visual Representations

编码智能体能通过渲染代码解决仓库级问题吗？一项关于视觉表示的探索性研究

Weijie Liang, Yuanfeng Song, Xing Chen, Caleb Chen Cao, Sirui Han, Yike Guo

专题命中 软件智能体 ：repository(title,abstract)；coding agent(title,abstract)；分类 cs.AI

AI总结 本研究探索将渲染代码作为编码智能体的操作上下文，基于 SWE-bench Verified 实验发现其可降低提示 token 成本但受模型架构限制，仅在原始代码读取为瓶颈时有用，是可行但有条件的压缩机制。

Comments 8 pages of main content

VulnGym: Benchmarking Coding Agents for Repository-Level Vulnerability Detection

VulnGym：面向代码智能体的仓库级漏洞检测基准测试

Kexing Ji, Jiachen Liu, Enze Hu, Cuiyun Gao, Keke Lian, Yongheng Liu, Lei Zhang, Tian Dong, Hao Chen, Wang Bin

专题命中 软件智能体 ：repository(title,abstract)；coding agent(title,abstract)；分类 cs.SE

AI总结 研究人员提出VulnGym基准，解决现有基准难以评估代码智能体仓库级漏洞检测能力的问题，发现当前代码智能体在该检测及支撑追踪构建上仍存在局限。