代码大模型 / AI 编程

Natural Language Generation and Understanding of Big Code for AI-Assisted Programming: A Review

Man Fai Wong, Shangxin Guo, Ching Nam Hang, Siu Wai Ho, Chee Wei Tan

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

Journal ref Entropy(2023), 25(6), 888

Exploring the Robustness of Large Language Models for Solving Programming Problems

Atsushi Shirafuji, Yutaka Watanobe, Takumi Ito, Makoto Morishita, Yuki Nakamura, Yusuke Oda, Jun Suzuki

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

Compositional Exemplars for In-context Learning

Jiacheng Ye, Zhiyong Wu, Jiangtao Feng, Tao Yu, Lingpeng Kong

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

Comments Accepted in ICML 2023

Analysis of ChatGPT on Source Code

Ahmed R. Sadik, Antonello Ceravola, Frank Joublin, Jibesh Patra

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

Comments 40 pages, examples provided for each experiment. arXiv admin note: text overlap with arXiv:2107.03374 by other authors

CodeT5+: Open Code Large Language Models for Code Understanding and Generation

Yue Wang, Hung Le, Akhilesh Deepak Gotmare, Nghi D. Q. Bui, Junnan Li, Steven C. H. Hoi

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

Comments 26 pages, preprint

Does Synthetic Data Generation of LLMs Help Clinical Text Mining?

Ruixiang Tang, Xiaotian Han, Xiaoqian Jiang, Xia Hu

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

Comments 10 pages, 8 tables, 4 figures

InCoder: A Generative Model for Code Infilling and Synthesis

Daniel Fried, Armen Aghajanyan, Jessy Lin, Sida Wang, Eric Wallace, Freda Shi, Ruiqi Zhong, Wen-tau Yih, Luke Zettlemoyer, Mike Lewis

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

Comments ICLR 2023. v3: camera-ready that includes PLBART and OpenAI baselines

WikiCoder: Learning to Write Knowledge-Powered Code

Théo Matricon, Nathanaël Fijalkow, Gaëtan Margueritte

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

Comments Published in the proceedings of SPIN 2023

Large Language Models Are Human-Level Prompt Engineers

Yongchao Zhou, Andrei Ioan Muresanu, Ziwen Han, Keiran Paster, Silviu Pitis, Harris Chan, Jimmy Ba

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

Learning Deep Semantics for Test Completion

Pengyu Nie, Rahul Banerjee, Junyi Jessy Li, Raymond J. Mooney, Milos Gligoric

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

Comments Accepted as a conference paper in ICSE 2023

SantaCoder: don't reach for the stars!

Loubna Ben Allal, Raymond Li, Denis Kocetkov, Chenghao Mou, Christopher Akiki, Carlos Munoz Ferrandis, Niklas Muennighoff, Mayank Mishra, Alex Gu, Manan Dey, Logesh Kumar Umapathi, Carolyn Jane Anderson, Yangtian Zi, Joel Lamy Poirier, Hailey Schoelkopf, Sergey Troshin, Dmitry Abulkhanov, Manuel Romero, Michael Lappert, Francesco De Toni, Bernardo García del Río, Qian Liu, Shamik Bose, Urvashi Bhattacharyya, Terry Yue Zhuo, Ian Yu, Paulo Villegas, Marco Zocca, Sourab Mangrulkar, David Lansky, Huu Nguyen, Danish Contractor, Luis Villa, Jia Li, Dzmitry Bahdanau, Yacine Jernite, Sean Hughes, Daniel Fried, Arjun Guha, Harm de Vries, Leandro von Werra

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

PADL: Language-Directed Physics-Based Character Control

Jordan Juravsky, Yunrong Guo, Sanja Fidler, Xue Bin Peng

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

Generation-Augmented Query Expansion For Code Retrieval

Dong Li, Yelong Shen, Ruoming Jin, Yi Mao, Kuan Wang, Weizhu Chen

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

Capturing Failures of Large Language Models via Human Cognitive Biases

Erik Jones, Jacob Steinhardt

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

Comments Published at NeurIPS 2022

Probing Pretrained Models of Source Code

Sergey Troshin, Nadezhda Chirkova

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

When Language Model Meets Private Library

Daoguang Zan, Bei Chen, Zeqi Lin, Bei Guan, Yongji Wang, Jian-Guang Lou

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

Comments EMNLP 2022 Findings

Leveraging Language to Learn Program Abstractions and Search Heuristics

Catherine Wong, Kevin Ellis, Joshua B. Tenenbaum, Jacob Andreas

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

Comments appeared in Thirty-eighth International Conference on Machine Learning (ICML 2021)

Learning to Synthesize Programs as Interpretable and Generalizable Policies

Dweep Trivedi, Jesse Zhang, Shao-Hua Sun, Joseph J. Lim

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

Comments NeurIPS 2021. 53 pages, 16 figures, 12 tables. Website at https://clvrai.github.io/leaps/

Explanatory Learning: Beyond Empiricism in Neural Networks

Antonio Norelli, Giorgio Mariani, Luca Moschella, Andrea Santilli, Giambattista Parascandolo, Simone Melzi, Emanuele Rodolà

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

Comments Main paper: 10 pages, References: 3 pages, Appendix: 7 pages

Measuring Coding Challenge Competence With APPS

Dan Hendrycks, Steven Basart, Saurav Kadavath, Mantas Mazeika, Akul Arora, Ethan Guo, Collin Burns, Samir Puranik, Horace He, Dawn Song, Jacob Steinhardt

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

Comments NeurIPS 2021. Code and the APPS dataset is available at https://github.com/hendrycks/apps

SpreadsheetCoder: Formula Prediction from Semi-structured Context

Xinyun Chen, Petros Maniatis, Rishabh Singh, Charles Sutton, Hanjun Dai, Max Lin, Denny Zhou

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

Comments Published in ICML 2021

Representing Partial Programs with Blended Abstract Semantics

Maxwell Nye, Yewen Pu, Matthew Bowers, Jacob Andreas, Joshua B. Tenenbaum, Armando Solar-Lezama

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

Comments ICLR 2021

Imitation-Projected Programmatic Reinforcement Learning

Abhinav Verma, Hoang M. Le, Yisong Yue, Swarat Chaudhuri

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

Comments Published in Advances in Neural Information Processing Systems (NeurIPS) 2019

Sequence Model Design for Code Completion in the Modern IDE

Gareth Ari Aye, Gail E. Kaiser

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

Stepping Stones to Inductive Synthesis of Low-Level Looping Programs

Christopher D. Rosin

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

Comments AAAI 2019

Towards Synthesizing Complex Programs from Input-Output Examples

Xinyun Chen, Chang Liu, Dawn Song

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

Comments Published as a conference paper at ICLR 2018

Neural Program Search: Solving Programming Tasks from Description and Examples

Illia Polosukhin, Alexander Skidanov

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

Comments 9 pages, 3 figures, ICLR workshop

Navigating Large-Scale Document Collections: MuDABench for Multi-Document Analytical QA

在大规模文档集合中导航：MuDABench用于多文档分析问答

Zhanli Li, Yixuan Cao, Lvzhou Luo, Ping Luo

机构 * State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences (CAS)（人工智能安全国家重点实验室，计算技术研究所，中国科学院） ； University of Chinese Academy of Sciences（中国科学院大学） ； Wenlan School of Business, Zhongnan University of Economics and Law（中南财经政法大学文澜商学院） 纠错

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

AI总结 本文提出在大规模半结构化文档集合上进行分析问答的任务，介绍了MuDABench多文档分析问答基准，要求跨多个文档提取和综合信息以进行定量分析，实验发现标准RAG系统表现不佳，提出多代理工作流以提升性能。

Comments Findings of ACL 2026. The camera-ready version corrects some labeling errors. The accompanying repository is continuously updated based on community feedback; for the most up-to-date implementation and results, please refer to the repository

Large Language Model-Brained GUI Agents: A Survey

Chaoyun Zhang, Shilin He, Jiaxu Qian, Bowen Li, Liqun Li, Si Qin, Yu Kang, Minghua Ma, Guyue Liu, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang

机构 * Microsoft（微软公司） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； Peking University（北京大学） 纠错

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

Comments The collection of papers reviewed in this survey will be hosted and regularly updated on the GitHub repository: https://github.com/vyokky/LLM-Brained-GUI-Agents-Survey Additionally, a searchable webpage is available at https://aka.ms/gui-agent for easier access and exploration

Probing the Prefill: Detecting Code Vulnerabilities via Latent Activations

探测预填充：通过潜在激活检测代码漏洞

Alizishaan Khatri

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

AI总结 该研究从四个LLM提取预填充标记激活训练MLP探测器，在四个代码漏洞基准上实现平均F1值41.7%，证明LLM自身代码表示含漏洞信息，为轻量原生筛查提供方向。