代码大模型 / AI 编程

Shellcode_IA32: A Dataset for Automatic Shellcode Generation

Pietro Liguori, Erfan Al-Hossami, Domenico Cotroneo, Roberto Natella, Bojan Cukic, Samira Shaikh

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

Comments Paper accepted to NLP4Prog Workshop 2021 co-located with ACL-IJCNLP 2021. Extended journal version of this work has been published in the Automated Software Engineering journal, Volume 29, Article no. 30, March 2022, DOI: 10.1007/s10515-022-00331-3

Jigsaw: Large Language Models meet Program Synthesis

Naman Jain, Skanda Vaidyanath, Arun Iyer, Nagarajan Natarajan, Suresh Parthasarathy, Sriram Rajamani, Rahul Sharma

专题命中 代码生成 ：program synthesis(title)；分类 cs.SE、cs.PL

Comments Accepted to ICSE'22

A Case Study of LLVM-Based Analysis for Optimizing SIMD Code Generation

Joseph Huber, Weile Wei, Giorgis Georgakoudis, Johannes Doerfert, Oscar Hernandez

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

Code Generation from Natural Language with Less Prior and More Monolingual Data

Sajad Norouzi, Keyi Tang, Yanshuai Cao

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

Comments ACL 2021

Program Synthesis Over Noisy Data with Guarantees

Shivam Handa, Martin Rinard

专题命中 代码生成 ：program synthesis(title)；分类 cs.LG、cs.PL

Automatic code generation from sketches of mobile applications in end-user development using Deep Learning

Daniel Baulé, Christiane Gresse von Wangenheim, Aldo von Wangenheim, Jean C. R. Hauck, Edson C. Vargas Júnior

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

Comments 18 pages

Knowledge Refactoring for Inductive Program Synthesis

Sebastijan Dumancic, Tias Guns, Andrew Cropper

专题命中 代码生成 ：program synthesis(title)；分类 cs.AI、cs.LG

Comments 7 pages, 6 figures

IntelliCode Compose: Code Generation Using Transformer

Alexey Svyatkovskiy, Shao Kun Deng, Shengyu Fu, Neel Sundaresan

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

Comments Accepted for publication at ESEC/FSE conference

DeepVS: An Efficient and Generic Approach for Source Code Modeling Usage

Yasir Hussain, Zhiqiu Huang, Yu Zhou, Senzhang Wang

专题命中 代码生成 ：code model(title)；分类 cs.SE、cs.PL

Journal ref Electronics Letters ( Volume: 56 , Issue: 12 , 6 11 2020 ) Page(s): 604 - 607

Bayesian causal inference via probabilistic program synthesis

Sam Witty, Alexander Lew, David Jensen, Vikash Mansinghka

专题命中 代码生成 ：program synthesis(title)；分类 cs.AI、cs.LG

One-shot Information Extraction from Document Images using Neuro-Deductive Program Synthesis

Vishal Sunder, Ashwin Srinivasan, Lovekesh Vig, Gautam Shroff, Rohit Rahul

专题命中 代码生成 ：program synthesis(title)；分类 cs.AI、cs.LG

Comments 11 pages, appears in the 13th International Workshop on Neural-Symbolic Learning and Reasoning at IJCAI 2019

One DSL to Rule Them All: IDE-Assisted Code Generation for Agile Data Analysis

Artur Andrzejak, Oliver Wenz, Diego Costa

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

Comments 7 pages

Automatic Program Synthesis of Long Programs with a Learned Garbage Collector

Amit Zohar, Lior Wolf

专题命中 代码生成 ：program synthesis(title)；分类 cs.LG、cs.PL

Comments Published at NIPS 2018

Glass-Box Program Synthesis: A Machine Learning Approach

Konstantina Christakopoulou, Adam Tauman Kalai

专题命中 代码生成 ：program synthesis(title)；分类 cs.AI、cs.LG

Code Generation for Cryptographic Kernels using Multi-word Modular Arithmetic on GPU

Naifeng Zhang, Franz Franchetti

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

Comments Accepted at the International Symposium on Code Generation and Optimization (CGO), 2025

OpenClassGen: A Large-Scale Corpus of Real-World Python Classes for LLM Research

OpenClassGen: 一个大规模的真实世界Python类语料库用于大语言模型研究

Musfiqur Rahman, SayedHassan Khatoonabadi, Emad Shihab

机构 * Concordia University（康科德大学） 纠错

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

AI总结 OpenClassGen提供324,843个Python类的语料库，用于评估大语言模型的代码生成能力，通过类骨架和静态代码度量指标，支持多种应用场景。

Comments This paper has been accepted for publication at the 30th International Conference on Evaluation and Assessment in Software Engineering (EASE 2026) AI models/data track

SEVerA: Verified Synthesis of Self-Evolving Agents

SEVerA: 验证合成自进化代理

Debangshu Banerjee, Changming Xu, Eugene Ie, Ming Zhang, Daiyi Peng, Chu-Cheng Lin, Gagandeep Singh

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； Google（谷歌） 纠错

专题命中 代码生成 ：code generation(abstract)；program repair(abstract)；分类 cs.SE、cs.LG、cs.PL

AI总结 SEVerA通过引入形式化guarded生成模型，结合搜索、验证和学习三阶段框架，在程序验证、符号数学合成等任务中实现零约束违规，提升自进化代理的正确性和性能。

Comments First Formally Verified Self-Evolving LLM Agents

SimLLM: Fine-Tuning Code LLMs for SimPy-Based Queueing System Simulation

SimLLM：用于基于SimPy的排队系统模拟的代码LLM微调

Jun-Qi Chen, Kun Zhang, Rui Zheng, Ying Zhong

机构 * Institute of Statistics and Big Data, Renmin University of China（中国人民大学统计与大数据研究院） ； School of Information, Renmin University of China（中国人民大学信息学院） ； School of Management and Economics, University of Electronic Science and Technology of China（电子科技大学管理学院） 纠错

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

AI总结 SimLLM通过微调开源LLM提升SimPy排队系统模拟代码生成能力，提供替代闭源模型的可行方案。

Comments 33 pages, 10 figures

State-of-the-art Small Language Coder Model: Mify-Coder

最先进的小型语言编码器模型：Mify-Coder

Abhinav Parmar, Abhisek Panigrahi, Abhishek Kumar Dwivedi, Abhishek Bhattacharya, Adarsh Ramachandra, Aditya Choudhary, Aditya Garg, Aditya Raj, Alankrit Bhatt, Alpesh Yadav, Anant Vishnu, Ananthu Pillai, Ankush Kumar, Aryan Patnaik, Aswatha Narayanan S, Avanish Raj Singh, Bhavya Shree Gadda, Brijesh Pankajbhai Kachhadiya, Buggala Jahnavi, Chidurala Nithin Krishna, Chintan Shah, Chunduru Akshaya, Debarshi Banerjee, Debrup Dey, Deepa R., Deepika B G, Faiz ur Rahman, Gagan Gayari, Gudhi Jagadeesh Kumar Naidu, Gursimar Singh, Harshal Tyagi, Harshini K, James Mani Vathalloor, Jayarama Nettar, Jayashree Gajjam, Joe Walter Sugil George, Kamalakara Sri Krishna Tadepalli, Kamalkumar Rathinasamy, Karan Chaurasia, Karthikeyan S, Kashish Arora, Kaushal Desai, Khushboo Buwade, Kiran Manjrekar, Malikireddy Venkata Sai Likhitha, Manjunath A, Mitali Mahavir Bedmutha, Mohammed Rafee Tarafdar, Nikhil Tiwari, Nikitha K Gigi, Pavan Ravikumar, Pendyala Swarnanjali, Piyush Anand, Prakash Chandrasekar, Prasanna Bhalchandra Gawade, Prasanth Sivan, Preeti Khurana, Priyanshi Babbar, Rajab Ali Mondal, Rajesh Kumar Vissapragada, Rajeshwari Ganesan, Rajeswari Koppisetti, Ramjee R., Ramkumar Thiruppathisamy, Rani G. S., S Reka, Samarth Gupta, Sandeep Reddy Kothakota, Sarathy K, Sathyanarayana Sampath Kumar, Saurabh Kumar, Shashank Khasare, Shenbaga Devi Venkatesh Kumar, Shiva Rama Krishna Parvatham, Shoeb Shaikh, Shrishanmathi A, Shubham Pathak, Sree Samhita Koppaka, Sreenivasa Raghavan K S, Sreeram Venkatasubramanian, Suprabha Desai Bojja, Swetha R, Syed Ahmed, Chinmai Harshitha Thota, Tushar Yadav, Veeravelly Kusumitha, V V S S Prasanth Patnaik, Vidya Sri Sesetti, Vijayakeerthi K, Vikram Raj Bakshi, Vinay K K, Vinoth Kumar Loganathan, Vipin Tiwari, Vivek Kumar Shrivastav, V Venkata Sri Datta Charan, Wasim Akhtar Khan

机构 * Infosys AI Research（英矽斯人工智能研究院） ； Mify Team（Mify团队） 纠错

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

AI总结 Mify-Coder通过高效训练策略和数据优化，在保持高准确性和安全性的同时，实现了比更大模型更优的代码生成性能。

SLMFix: Leveraging Small Language Models for Error Fixing with Reinforcement Learning

SLMFix：利用小型语言模型通过强化学习进行错误修复

David Jiahao Fu, Aryan Gupta, Aaron Councilman, David Grove, Yu-Xiong Wang, Vikram Adve

专题命中 代码生成 ：code generation(abstract)；program repair(abstract)；分类 cs.SE、cs.AI、cs.PL

AI总结 SLMFix通过强化学习微调小型语言模型，有效修复LLMs生成代码的语法错误，提升领域特定语言代码质量，优于传统微调方法。

QiMeng-Xpiler: Transcompiling Tensor Programs for Deep Learning Systems with a Neural-Symbolic Approach

Shouyang Dong, Yuanbo Wen, Jun Bi, Di Huang, Jiaming Guo, Jianxing Xu, Ruibai Xu, Xinkai Song, Yifan Hao, Xuehai Zhou, Tianshi Chen, Qi Guo, Yunji Chen

机构 * University of Science and Technology of China（科学技术大学） ； Cambricon Technologies（Cambricon科技） ； SKL of Processors, Institute of Computing Technology, Chinese Academy of Sciences（处理器实验室，计算技术研究所，中国科学院） ； Institute of Software, Chinese Academy of Sciences（软件研究所，中国科学院） 纠错

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

Comments Accepted to OSDI 2025

Towards a Classification of Open-Source ML Models and Datasets for Software Engineering

Alexandra González, Xavier Franch, David Lo, Silverio Martínez-Fernández

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

Comments 5 pages, 8 figures

SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning

Yangruibo Ding, Jinjun Peng, Marcus J. Min, Gail Kaiser, Junfeng Yang, Baishakhi Ray

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

Comments NeurIPS 2024 Camera-ready

Statically Contextualizing Large Language Models with Typed Holes

Andrew Blinn, Xiang Li, June Hyung Kim, Cyrus Omar

专题命中 代码生成 ：code generation(abstract)；program synthesis(abstract)；分类 cs.SE、cs.AI、cs.PL

Comments To appear at OOPSLA2024

Journal ref Proceedings of the ACM on Programming Languages, Volume 8, 2024; Issue OOPSLA2 Article No.: 288, Pages 468 - 498

Mitigating Gender Bias in Code Large Language Models via Model Editing

Zhanyue Qin, Haochuan Wang, Zecheng Wang, Deyuan Liu, Cunhang Fan, Zhao Lv, Zhiying Tu, Dianhui Chu, Dianbo Sui

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

DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence

Daya Guo, Qihao Zhu, Dejian Yang, Zhenda Xie, Kai Dong, Wentao Zhang, Guanting Chen, Xiao Bi, Y. Wu, Y. K. Li, Fuli Luo, Yingfei Xiong, Wenfeng Liang

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

Programming Puzzles

Tal Schuster, Ashwin Kalyan, Oleksandr Polozov, Adam Tauman Kalai

专题命中 代码生成 ：program synthesis(abstract)；分类 cs.SE、cs.CL、cs.AI；repository(comments)

Comments NeurIPS 2021 (Datasets and Benchmarks Track). Puzzles repository: https://github.com/microsoft/PythonProgrammingPuzzles

Drawing-Recode: Annotation Grounding for Parametric CAD Code Generation from Raster 2D CAD Drawings

Drawing-Recode：基于栅格2D CAD图纸的参数化CAD代码生成的标注定位方法

Mingi Kim, Yongjun Kim, Hyungki Kim

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

AI总结 Drawing-Recode是一种从栅格2D CAD图纸生成参数化CAD代码的框架，通过图像编码器、文本识别模块、交叉注意力与AGL实现标注定位，性能优于基线且对工业扫描图纸鲁棒，可助力制造自动化。

ARCANA: A Reflective Multi-Agent Program Synthesis Framework for ARC-AGI-2 Reasoning

ARCANA：用于ARC-AGI-2推理的反射式多智能体程序合成框架

Kunbo Zhang, Lei Fu, Zeyu Wang, Zijing Liu, Kejian Tong

机构 * Columbia University（哥伦比亚大学） ； University of California, Los Angeles（加州大学洛杉矶分校） ； Northeastern University（东北大学） 纠错

专题命中 代码生成 ：program synthesis(title)；分类 cs.AI

AI总结 ARCANA是用于ARC-AGI-2推理的多智能体框架，将任务分解为感知、假设生成等步骤，智能体通过可微黑板通信，由元控制器调度。其设计结合程序搜索与校正，提升了抽象转换任务的推理效率和解决方案质量。

From Failing to Passing: Evolving Natural Language Prompt Optimization Rules for LLM Code Generation

从失败到通过：为大语言模型代码生成演化自然语言提示优化规则

Amal Akli, Melissa Akli, Cedric Richter, Mike Papadakis, Yves Le Traon

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

AI总结 研究大语言模型提示敏感性，用搜索法演化自然语言转换规则，提出DUALFIX管道，结合规则与执行反馈修复，可跨问题跨模型使用，提升代码生成性能。