代码大模型 / AI 编程 - arXivDaily 专题

2503.23145 2025-08-11 cs.PL cs.AI cs.CL cs.LG 83%

CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis

Anjiang Wei, Tarun Suresh, Jiannan Cao, Naveen Kannan, Yuheng Wu, Kai Yan, Thiago S. F. X. Teixeira, Ke Wang, Alex Aiken

机构 * Stanford University（斯坦福大学）； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）； MIT（麻省理工学院）； Intel（英特尔）； Nanjing University（南京大学）

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

2408.09121 2025-07-29 cs.LG cs.AI cs.CL cs.SE 83%

Selective Prompt Anchoring for Code Generation

Yuan Tian, Tianyi Zhang

机构 * Purdue University（普渡大学）

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

Comments Accepted by ICML'25

2506.11006 2025-06-16 cs.SE 83%

Test code generation at Ericsson using Program Analysis Augmented Fine Tuned LLMs

Sai Krishna, Balvinder Singh, Sujoy Roychowdhury, Giriprasad Sridhara, Sourav Mazumdar, Magnus Sandelin, Dimitris Rentas, Maciej Nalepa, Karol Sawicki, Jakub Gajda

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

Comments Accepted at International Conference on Evaluation and Assessment in Software Engineering (EASE), 2025

2412.15118 2025-06-09 cs.CL cs.AI cs.LG cs.SE 83%

Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation

Zhuohao Yu, Weizheng Gu, Yidong Wang, Xingru Jiang, Zhengran Zeng, Jindong Wang, Wei Ye, Shikun Zhang

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

Comments Accepted to ICML 2025; 23 pages, 7 figures, code is available at: https://github.com/zhuohaoyu/ORPS

2505.10402 2025-05-16 cs.CL cs.AI cs.LG cs.SE 83%

Rethinking Repetition Problems of LLMs in Code Generation

Yihong Dong, Yuchen Liu, Xue Jiang, Zhi Jin, Ge Li

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

Comments Accepted to ACL 2025 (main)

2505.06880 2025-05-13 cs.SE 83%

Benchmarking and Revisiting Code Generation Assessment: A Mutation-Based Approach

Longtian Wang, Tianlin Li, Xiaofei Xie, Yuhan Zhi, Jian Wang, Chao Shen

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

Comments 8 pages, 4 figures

2504.04351 2025-04-08 cs.SE cs.AI cs.CL cs.LG 83%

DDPT: Diffusion-Driven Prompt Tuning for Large Language Model Code Generation

Jinyang Li, Sangwon Hyun, M. Ali Babar

机构 * University of Adelaide（阿德莱德大学）

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

Comments ICSE CAIN 2025

2504.04220 2025-04-08 cs.SE 83%

AdaCoder: An Adaptive Planning and Multi-Agent Framework for Function-Level Code Generation

Yueheng Zhu, Chao Liu, Xuan He, Xiaoxue Ren, Zhongxin Liu, Ruwei Pan, Hongyu Zhang

专题命中代码生成：code generation(title,abstract)；coding agent(abstract)；分类 cs.SE

2503.20589 2025-03-27 cs.SE 83%

What to Retrieve for Effective Retrieval-Augmented Code Generation? An Empirical Study and Beyond

Wenchao Gu, Juntao Chen, Yanlin Wang, Tianyue Jiang, Xingzhe Li, Mingwei Liu, Xilin Liu, Yuchi Ma, Zibin Zheng

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

2501.13742 2025-01-24 cs.SE 83%

An Empirical Study of Retrieval-Augmented Code Generation: Challenges and Opportunities

Zezhou Yang, Sirong Chen, Cuiyun Gao, Zhenhao Li, Xing Hu, Kui Liu, Xin Xia

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

Comments This paper is accepted by TOSEM

2501.06283 2025-01-14 cs.SE cs.AI cs.CL cs.LO cs.PL 83%

Dafny as Verification-Aware Intermediate Language for Code Generation

Yue Chen Li, Stefan Zetzsche, Siva Somayyajula

机构 * Massachusetts Institute of Technology（麻省理工学院）； Amazon（亚马逊公司）

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

2308.11161 2024-11-01 cs.SE 83%

Adversarial Attacks on Code Models with Discriminative Graph Patterns

Thanh-Dat Nguyen, Yang Zhou, Xuan Bach D. Le, Patanamon Thongtanunam, David Lo

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

2407.02518 2024-10-30 cs.SE cs.AI cs.CL cs.CR cs.MA cs.PL 83%

INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness

Hung Le, Yingbo Zhou, Caiming Xiong, Silvio Savarese, Doyen Sahoo

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

Comments Accepted to The Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024)

2410.14766 2024-10-22 cs.SE cs.AI cs.ET cs.LG cs.PL 83%

Evaluating Quantized Large Language Models for Code Generation on Low-Resource Language Benchmarks

Enkhbold Nyamsuren

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

2310.01166 2024-10-16 cs.SE cs.CR 83%

Gotcha! This Model Uses My Code! Evaluating Membership Leakage Risks in Code Models

Zhou Yang, Zhipeng Zhao, Chenyu Wang, Jieke Shi, Dongsum Kim, Donggyun Han, David Lo

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

Comments Accepted by IEEE Transactions on Software Engineering, Camera-Ready Version

2404.08029 2024-10-08 cs.LG cs.AI cs.PL cs.SE 83%

A Multi-Expert Large Language Model Architecture for Verilog Code Generation

Bardia Nadimi, Hao Zheng

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

2409.06446 2024-09-11 cs.CR cs.AI cs.CL cs.LG cs.SE 83%

HexaCoder: Secure Code Generation via Oracle-Guided Synthetic Training Data

Hossein Hajipour, Lea Schönherr, Thorsten Holz, Mario Fritz

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

Comments 24 pages, 16 tables, 8 figures

2409.00856 2024-09-04 cs.SE cs.AI cs.CL cs.PL 83%

Benchmarking LLM Code Generation for Audio Programming with Visual Dataflow Languages

William Zhang, Maria Leon, Ryan Xu, Adrian Cardenas, Amelia Wissink, Hanna Martin, Maya Srikanth, Kaya Dorogi, Christian Valadez, Pedro Perez, Citlalli Grijalva, Corey Zhang, Mark Santolucito

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

2405.19787 2024-06-03 cs.CL cs.AI cs.LG cs.LO cs.PL 83%

From Symbolic Tasks to Code Generation: Diversification Yields Better Task Performers

Dylan Zhang, Justin Wang, Francois Charton

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

2304.07590 2024-05-14 cs.SE 83%

Self-collaboration Code Generation via ChatGPT

Yihong Dong, Xue Jiang, Zhi Jin, Ge Li

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

Comments Accepted to TOSEM

2404.02183 2024-04-04 cs.SE cs.AI cs.CL cs.LG cs.MA 83%

Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization

Yoichi Ishibashi, Yoshimasa Nishimura

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

2310.03173 2024-03-20 cs.CL 83%

$\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis

Zishun Yu, Yunzhe Tao, Liyu Chen, Tao Sun, Hongxia Yang

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

2306.09896 2024-02-05 cs.CL cs.AI cs.PL cs.SE 83%

Is Self-Repair a Silver Bullet for Code Generation?

Theo X. Olausson, Jeevana Priya Inala, Chenglong Wang, Jianfeng Gao, Armando Solar-Lezama

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

Comments Accepted to ICLR 2024. Added additional Code Llama experiments and fixed a data processing error harming Code Llama's reported self-repair performance on HumanEval

2401.15545 2024-01-30 cs.SE cs.AI cs.CL cs.PL 83%

PPM: Automated Generation of Diverse Programming Problems for Benchmarking Code Generation Models

Simin Chen, Xiaoning Feng, Xiaohong Han, Cong Liu, Wei Yang

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

Comments This paper has been accepted to The ACM International Conference on the Foundations of Software Engineering FSE 2024

2401.08683 2024-01-18 cs.AR cs.AI cs.LG cs.PL cs.SE 83%

Zero-Shot RTL Code Generation with Attention Sink Augmented Large Language Models

Selim Sandal, Ismail Akturk

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

2312.14875 2023-12-25 math.NA cs.AI cs.CE cs.FL cs.NA cs.NE 83%

Automating the Design of Multigrid Methods with Evolutionary Program Synthesis

Jonas Schmitt

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

2310.17680 2023-11-02 cs.SE cs.AI cs.CL cs.PL 83%

CodeFusion: A Pre-trained Diffusion Model for Code Generation

Mukul Singh, José Cambronero, Sumit Gulwani, Vu Le, Carina Negreanu, Gust Verbruggen

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

Comments Contains inappropriately sourced conjecture of OpenAI's ChatGPT parameter count from www.forbes.com/sites/forbestechcouncil/2023/02/17/is-bigger-better-why-the-chatgpt-vs-gpt-3-vs-gpt-4-battle-is-just-a-family-chat, a citation which was omitted. The authors do not have direct knowledge or verification of this information, and relied solely on this article, which may lead to public confusion

2303.12570 2023-10-23 cs.CL cs.AI cs.PL cs.SE 83%

RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation

Fengji Zhang, Bei Chen, Yue Zhang, Jacky Keung, Jin Liu, Daoguang Zan, Yi Mao, Jian-Guang Lou, Weizhu Chen

专题命中代码生成：repository(title,abstract)；分类 cs.SE、cs.CL、cs.AI

Comments accepted by EMNLP 2023 main conference

2309.17446 2023-10-03 cs.CL cs.LG cs.PL cs.SE 83%

L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language Models

Ansong Ni, Pengcheng Yin, Yilun Zhao, Martin Riddell, Troy Feng, Rui Shen, Stephen Yin, Ye Liu, Semih Yavuz, Caiming Xiong, Shafiq Joty, Yingbo Zhou, Dragomir Radev, Arman Cohan

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

Comments Project Website: https://l2c-eval.github.io/

2302.08468 2023-09-04 cs.LG cs.CL cs.PL cs.SE 83%

LEVER: Learning to Verify Language-to-Code Generation with Execution

Ansong Ni, Srini Iyer, Dragomir Radev, Ves Stoyanov, Wen-tau Yih, Sida I. Wang, Xi Victoria Lin

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

Comments ICML'23; code available at https://github.com/niansong1996/lever

1. 代码生成 4132 篇

CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis

Selective Prompt Anchoring for Code Generation

Test code generation at Ericsson using Program Analysis Augmented Fine Tuned LLMs

Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation

Rethinking Repetition Problems of LLMs in Code Generation

Benchmarking and Revisiting Code Generation Assessment: A Mutation-Based Approach

DDPT: Diffusion-Driven Prompt Tuning for Large Language Model Code Generation

AdaCoder: An Adaptive Planning and Multi-Agent Framework for Function-Level Code Generation

What to Retrieve for Effective Retrieval-Augmented Code Generation? An Empirical Study and Beyond

An Empirical Study of Retrieval-Augmented Code Generation: Challenges and Opportunities

Dafny as Verification-Aware Intermediate Language for Code Generation

Adversarial Attacks on Code Models with Discriminative Graph Patterns

INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness

Evaluating Quantized Large Language Models for Code Generation on Low-Resource Language Benchmarks

Gotcha! This Model Uses My Code! Evaluating Membership Leakage Risks in Code Models

A Multi-Expert Large Language Model Architecture for Verilog Code Generation

HexaCoder: Secure Code Generation via Oracle-Guided Synthetic Training Data

Benchmarking LLM Code Generation for Audio Programming with Visual Dataflow Languages

From Symbolic Tasks to Code Generation: Diversification Yields Better Task Performers

Self-collaboration Code Generation via ChatGPT

Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization

$\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis

Is Self-Repair a Silver Bullet for Code Generation?

PPM: Automated Generation of Diverse Programming Problems for Benchmarking Code Generation Models

Zero-Shot RTL Code Generation with Attention Sink Augmented Large Language Models

Automating the Design of Multigrid Methods with Evolutionary Program Synthesis

CodeFusion: A Pre-trained Diffusion Model for Code Generation

RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation

L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language Models

LEVER: Learning to Verify Language-to-Code Generation with Execution