代码大模型 / AI 编程 - arXivDaily 专题

2503.20840 2025-08-07 cs.AI cs.CL cs.LG cs.SE 70%

CodeTool: Enhancing Programmatic Tool Invocation of LLMs via Process Supervision

Yifei Lu, Fanghua Ye, Jian Li, Qiang Gao, Cheng Liu, Haibo Luo, Nan Du, Xiaolong Li, Feiliang Ren

机构 * Northeastern University（东北大学）； Hunyuan AI Digital Human（文英AI数字人）

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

Comments ACL2025

2508.02968 2025-08-06 cs.SE 70%

Developer Perceptions on Utilising Low-Code Approaches to Build Accessible and Adaptive Applications for Seniors

Shavindra Wickramathilaka, John Grundy, Kashumi Madampe, Omar Haggag

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

Comments This paper has been submitted to ACM Transactions on Software Engineering and Methodology (TOSEM)

2503.10968 2025-07-22 cs.AI cs.CL cs.LG cs.SE 70%

Combinatorial Optimization for All: Using LLMs to Aid Non-Experts in Improving Optimization Algorithms

Camilo Chacón Sartori, Christian Blum

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

2507.13413 2025-07-21 cs.LG 70%

LightAutoDS-Tab: Multi-AutoML Agentic System for Tabular Data

Aleksey Lapin, Igor Hromov, Stanislav Chumakov, Mile Mitrovic, Dmitry Simakov, Nikolay O. Nikitin, Andrey V. Savchenko

机构 * Sber AI Lab（Sber AI实验室）； ITMO University（ITMO大学）

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

Comments 11 pages, 2 figures

2507.03620 2025-07-08 cs.SE cs.AI cs.CL cs.LG 70%

Is It Time To Treat Prompts As Code? A Multi-Use Case Study For Prompt Optimization Using DSPy

Francisca Lemos, Victor Alves, Filipa Ferraz

机构 * ALGORITMI Research Centre/LASI, University of Minho, Braga, 4710-057, Portugal（ALGORITMI研究中心/LASI，明霍大学，布拉加，4710-057，葡萄牙）

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

Comments 20 pages with 1 figure

2506.09657 2025-06-17 cs.CL 70%

Team Anotheroption at SemEval-2025 Task 8: Bridging the Gap Between Open-Source and Proprietary LLMs in Table QA

Nikolas Evkarpidi, Elena Tutubalina

机构 * HSE University（俄罗斯伏尔加格勒国立大学）； AIRI Sber AI Kazan Federal University（卡兹别克联邦大学）

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

Comments Accepted for publication at the 19th International Workshop on Semantic Evaluation (SemEval-2025), to be held in conjunction with ACL 2025. 15 pages, 5 figures; full paper title was added

2412.11014 2025-06-09 cs.LG cs.AI cs.AR cs.PL cs.SE 70%

CoopetitiveV: Leveraging LLM-powered Coopetitive Multi-Agent Prompting for High-quality Verilog Generation

Zhendong Mi, Renming Zheng, Haowen Zhong, Yue Sun, Seth Kneeland, Sayan Moitra, Ken Kutzer, Zhaozhuo Xu Shaoyi Huang

机构 * Stevens Institute of Technology（史蒂文斯理工学院）； University of Washington（华盛顿大学）； Amazon（亚马逊）； SambaNova Systems（SambaNova系统）

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

2502.11404 2025-06-02 cs.CL 70%

ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Models

Hanxing Ding, Shuchang Tao, Liang Pang, Zihao Wei, Jinyang Gao, Bolin Ding, Huawei Shen, Xueqi Cheng

机构 * State Key Laboratory of AI Safety, Institute of Computing Technology, 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）； Alibaba Group（阿里巴巴集团）

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

Comments Accepted to ACL 2025

2502.04350 2025-05-30 cs.CL cs.AI cs.LG cs.SC cs.SE 70%

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance

Yongchao Chen, Yilun Hao, Yueying Liu, Yang Zhang, Chuchu Fan

机构 * Massachusetts Institute of Technology, Boston, MA, USA（麻省理工学院）； Harvard University, Boston, MA, USA（哈佛大学）； MIT-IBM Watson AI Lab, Boston, MA, USA（MIT-IBM Watson AI实验室）； University of Illinois Urbana-Champaign, Urbana, IL, USA（伊利诺伊大学厄巴纳-香槟分校）

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

Comments 28 pages, 12 figures

Journal ref International Conference on Machine Learning (ICML'2025)

2502.10743 2025-05-26 cs.CL 70%

1bit-Merging: Dynamic Quantized Merging for Large Language Models

Shuqi Liu, Yuxuan Yao, Bowei He, Zehua Liu, Xiongwei Han, Mingxuan Yuan, Han Wu, Linqi Song

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

2408.03680 2025-05-21 cs.SE 70%

Smaller but Better: Self-Paced Knowledge Distillation for Lightweight yet Effective LCMs

Yujia Chen, Yang Ye, Zhongqi Li, Yuchi Ma, Cuiyun Gao

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

Comments Accepted by FSE 2025

2505.02275 2025-05-06 cs.SE 70%

A Path Less Traveled: Reimagining Software Engineering Automation via a Neurosymbolic Paradigm

Antonio Mastropaolo, Denys Poshyvanyk

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

2505.01067 2025-05-05 cs.CR cs.AI 70%

A Rusty Link in the AI Supply Chain: Detecting Evil Configurations in Model Repositories

Ziqi Ding, Qian Fu, Junchen Ding, Gelei Deng, Yi Liu, Yuekang Li

机构 * UNSW Sydney（新南威尔士大学）； Commonwealth Scientific and Industrial Research Organisation (CSIRO) Data61（澳大利亚联邦科学与工业研究组织（CSIRO）Data61）； Nanyang Technological University（南洋理工大学）； Quantstamp

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

2408.04820 2025-04-21 cs.SE cs.AI cs.CL cs.HC cs.LG 70%

Natural Language Outlines for Code: Literate Programming in the LLM Era

Kensen Shi, Deniz Altınbüken, Saswat Anand, Mihai Christodorescu, Katja Grünwedel, Alexa Koenings, Sai Naidu, Anurag Pathak, Marc Rasi, Fredde Ribeiro, Brandon Ruffin, Siddhant Sanyam, Maxim Tabachnyk, Sara Toth, Roy Tu, Tobias Welp, Pengcheng Yin, Manzil Zaheer, Satish Chandra, Charles Sutton

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

Comments Accepted to FSE'25 Industry Track

2503.14201 2025-03-19 cs.SE 70%

Why Personalizing Deep Learning-Based Code Completion Tools Matters

Alessandro Giagnorio, Alberto Martin-Lopez, Gabriele Bavota

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

Comments Accepted for publication at ACM TOSEM

2407.03157 2025-03-05 cs.CL cs.AI cs.LG cs.SE 70%

Let the Code LLM Edit Itself When You Edit the Code

Zhenyu He, Jun Zhang, Shengjie Luo, Jingjing Xu, Zhi Zhang, Di He

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

Comments ICLR 2025 Camera Ready

2310.10508 2025-02-21 cs.SE 70%

Prompt Engineering or Fine-Tuning: An Empirical Assessment of LLMs for Code

Jiho Shin, Clark Tang, Tahmineh Mohati, Maleknaz Nayebi, Song Wang, Hadi Hemmati

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

Comments 11 pages + reference. Accepted in 22nd International Conference on Mining Software Repositories, 2025. Technical Papers Track (MSR'25)

2410.02743 2025-02-18 cs.CL 70%

MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions

Yekun Chai, Haoran Sun, Huang Fang, Shuohuan Wang, Yu Sun, Hua Wu

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

2403.00894 2025-01-22 cs.SE cs.AI cs.CL cs.PL 70%

Comparing large language models and human programmers for generating programming code

Wenpin Hou, Zhicheng Ji

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

Journal ref Adv Sci (Weinh). 2024 Dec 30:e2412279. Epub ahead of print. PMID: 39736107

2405.12641 2024-12-02 cs.SE 70%

Fight Fire with Fire: How Much Can We Trust ChatGPT on Source Code-Related Tasks?

Xiao Yu, Lei Liu, Xing Hu, Jacky Wai Keung, Jin Liu, Xin Xia

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

2405.17503 2024-10-31 cs.SE cs.AI cs.CL cs.PL 70%

Code Repair with LLMs gives an Exploration-Exploitation Tradeoff

Hao Tang, Keya Hu, Jin Peng Zhou, Sicheng Zhong, Wei-Long Zheng, Xujie Si, Kevin Ellis

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

2405.15383 2024-10-31 cs.AI 70%

Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search

Nicola Dainese, Matteo Merler, Minttu Alakuijala, Pekka Marttinen

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

Comments Accepted at NeurIPS 2024, Main Track. 11 pages in main text, 40 pages including references and supplementary materials. 2 figures and 3 tables in the main text, 9 figures and 12 tables when including the supplementary materials. Website at https://sites.google.com/view/code-world-models/home

2312.13322 2024-09-23 cs.PL cs.AI cs.LG cs.SE 70%

MonoCoder: Domain-Specific Code Language Model for HPC Codes and Tasks

Tal Kadosh, Niranjan Hasabnis, Vy A. Vo, Nadav Schneider, Neva Krien, Mihai Capota, Abdul Wasay, Nesreen Ahmed, Ted Willke, Guy Tamir, Yuval Pinter, Timothy Mattson, Gal Oren

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

2405.03727 2024-09-10 cs.SE cs.AI cs.LG cs.PL 70%

Large Language Models Synergize with Automated Machine Learning

Jinglue Xu, Jialong Li, Zhen Liu, Nagar Anthel Venkatesh Suryanarayanan, Guoyuan Zhou, Jia Guo, Hitoshi Iba, Kenji Tei

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

Comments published at TMLR

2306.00229 2024-09-04 cs.PL 70%

Minotaur: A SIMD-Oriented Synthesizing Superoptimizer

Zhengyang Liu, Stefan Mada, John Regehr

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

Comments to appear in OOPSLA'24

2408.10334 2024-08-21 cs.AI 70%

A Disguised Wolf Is More Harmful Than a Toothless Tiger: Adaptive Malicious Code Injection Backdoor Attack Leveraging User Behavior as Triggers

Shangxi Wu, Jitao Sang

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

2404.00725 2024-07-26 cs.SE cs.AI cs.CL cs.LG 70%

The Larger the Better? Improved LLM Code-Generation via Budget Reallocation

Michael Hassid, Tal Remez, Jonas Gehring, Roy Schwartz, Yossi Adi

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

Comments COLM 2024

2406.03092 2024-06-06 cs.CL 70%

FragRel: Exploiting Fragment-level Relations in the External Memory of Large Language Models

Xihang Yue, Linchao Zhu, Yi Yang

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

2405.19032 2024-05-30 cs.AI cs.LG cs.PL cs.SE 70%

Large Language Models for Code Summarization

Balázs Szalontai, Gergő Szalay, Tamás Márton, Anna Sike, Balázs Pintér, Tibor Gregorics

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

Comments technical report with 11 pages, 1 figure, 10 tables

2404.06634 2024-04-11 cs.SE 70%

Perplexed: Understanding When Large Language Models are Confused

Nathan Cooper, Torsten Scholak

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

1. 代码生成 4122 篇

CodeTool: Enhancing Programmatic Tool Invocation of LLMs via Process Supervision

Developer Perceptions on Utilising Low-Code Approaches to Build Accessible and Adaptive Applications for Seniors

Combinatorial Optimization for All: Using LLMs to Aid Non-Experts in Improving Optimization Algorithms

LightAutoDS-Tab: Multi-AutoML Agentic System for Tabular Data

Is It Time To Treat Prompts As Code? A Multi-Use Case Study For Prompt Optimization Using DSPy

Team Anotheroption at SemEval-2025 Task 8: Bridging the Gap Between Open-Source and Proprietary LLMs in Table QA

CoopetitiveV: Leveraging LLM-powered Coopetitive Multi-Agent Prompting for High-quality Verilog Generation

ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Models

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance

1bit-Merging: Dynamic Quantized Merging for Large Language Models

Smaller but Better: Self-Paced Knowledge Distillation for Lightweight yet Effective LCMs

A Path Less Traveled: Reimagining Software Engineering Automation via a Neurosymbolic Paradigm

A Rusty Link in the AI Supply Chain: Detecting Evil Configurations in Model Repositories

Natural Language Outlines for Code: Literate Programming in the LLM Era

Why Personalizing Deep Learning-Based Code Completion Tools Matters

Let the Code LLM Edit Itself When You Edit the Code

Prompt Engineering or Fine-Tuning: An Empirical Assessment of LLMs for Code

MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions

Comparing large language models and human programmers for generating programming code

Fight Fire with Fire: How Much Can We Trust ChatGPT on Source Code-Related Tasks?

Code Repair with LLMs gives an Exploration-Exploitation Tradeoff

Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search

MonoCoder: Domain-Specific Code Language Model for HPC Codes and Tasks

Large Language Models Synergize with Automated Machine Learning

Minotaur: A SIMD-Oriented Synthesizing Superoptimizer

A Disguised Wolf Is More Harmful Than a Toothless Tiger: Adaptive Malicious Code Injection Backdoor Attack Leveraging User Behavior as Triggers

The Larger the Better? Improved LLM Code-Generation via Budget Reallocation

FragRel: Exploiting Fragment-level Relations in the External Memory of Large Language Models

Large Language Models for Code Summarization

Perplexed: Understanding When Large Language Models are Confused