代码大模型 / AI 编程 - arXivDaily 专题

2510.05158 2025-10-08 cs.AI cs.CE cs.LG cs.MA 62%

Lang-PINN: From Language to Physics-Informed Neural Networks via a Multi-Agent Framework

Xin He, Liangliang You, Hongduan Tian, Bo Han, Ivor Tsang, Yew-Soon Ong

机构 * Agency for Science, Technology and Research (A*STAR)（科技研究局）； Hong Kong Baptist University（香港 Baptist 大学）； North China Electric Power University（华北电力大学）

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

Comments PINN, PDE, Agent, LLM

2510.05148 2025-10-08 cs.CL cs.AI 62%

Every Step Counts: Decoding Trajectories as Authorship Fingerprints of dLLMs

Qi Li, Runpeng Yu, Haiquan Lu, Xinchao Wang

机构 * National University of Singapore（新加坡国立大学）

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

2510.05090 2025-10-07 cs.CL cs.AI 62%

Finish First, Perfect Later: Test-Time Token-Level Cross-Validation for Diffusion Large Language Models

Runchu Tian, Junxia Cui, Xueqiang Xu, Feng Yao, Jingbo Shang

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）； University of California San Diego（加州大学圣地亚哥分校）

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

Comments 17 pages, 8 figures. Work in progress

2506.02089 2025-10-07 cs.LG cs.AI cs.CR 62%

SALAD: Systematic Assessment of Machine Unlearning on LLM-Aided Hardware Design

Zeng Wang, Minghao Shao, Rupesh Karn, Likhitha Mankali, Jitendra Bhandari, Ramesh Karri, Ozgur Sinanoglu, Muhammad Shafique, Johann Knechtel

机构 * NYU Tandon School of Engineering（纽约大学Tandon工程学院）； NYU Abu Dhabi（纽约大学阿布扎克分校）

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

2510.03029 2025-10-06 cs.SE cs.AI 62%

Investigating The Smells of LLM Generated Code

Debalina Ghosh Paul, Hong Zhu, Ian Bayley

机构 * School of Engineering, Computing and Mathematics, Oxford Brookes University（工程、计算与数学学院，奥克斯福德布鲁克斯大学）

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

2510.02917 2025-10-06 cs.SE cs.LG 62%

Mechanistic Interpretability of Code Correctness in LLMs via Sparse Autoencoders

Kriz Tahimic, Charibeth Cheng

机构 * College of Computer Studies（计算机科学学院）

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

2510.01272 2025-10-03 cs.AI cs.LG 62%

Modeling Others' Minds as Code

Kunal Jha, Aydan Yuenan Huang, Eric Ye, Natasha Jaques, Max Kleiman-Weiner

机构 * Department of Computer Science, University of Washington（华盛顿大学计算机科学系）； Department of Computer Science, Johns Hopkins University（约翰霍普金斯大学计算机科学系）

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

2510.00911 2025-10-02 cs.LG cs.AI 62%

RiskPO: Risk-based Policy Optimization via Verifiable Reward for LLM Post-Training

Tao Ren, Jinyang Jiang, Hui Yang, Wan Tian, Minhao Zou, Guanghao Li, Zishi Zhang, Qinghao Wang, Shentao Qin, Yanjun Zhao, Rui Tao, Hui Shao, Yijie Peng

机构 * Peking University（北京大学）

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

2510.00373 2025-10-02 cs.LG cs.AI cs.NE cs.SY eess.SY 62%

Combining Large Language Models and Gradient-Free Optimization for Automatic Control Policy Synthesis

Carlo Bosio, Matteo Guarrera, Alberto Sangiovanni-Vincentelli, Mark W. Mueller

机构 * UC Berkeley, Department of Mechanical Engineering（伯克利大学机械工程系）

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

Comments 8 pages, 7 figures

2509.25604 2025-10-01 cs.CL cs.LG 62%

RFG: Test-Time Scaling for Diffusion Large Language Model Reasoning with Reward-Free Guidance

Tianlang Chen, Minkai Xu, Jure Leskovec, Stefano Ermon

机构 * Stanford University（斯坦福大学）

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

Comments 27 pages, 3 figures, 2 tables

2509.24160 2025-09-30 cs.RO cs.AI cs.LG 62%

Memory Transfer Planning: LLM-driven Context-Aware Code Adaptation for Robot Manipulation

Tomoyuki Kagaya, Subramanian Lakshmi, Yuxuan Lou, Thong Jing Yuan, Jayashree Karlekar, Sugiri Pranata, Natsuki Murakami, Akira Kinose, Yang You

机构 * Panasonic Connect Co., Ltd.（松下电器（控股）公司）； Panasonic R&D Center（松下研发中心）； National University of Singapore（新加坡国立大学）

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

2505.18777 2025-09-29 cs.LG cs.AI 62%

HD-PiSSA: High-Rank Distributed Orthogonal Adaptation

Yiding Wang, Fauxu Meng, Xuefeng Zhang, Fan Jiang, Pingzhi Tang, Muhan Zhang

机构 * Institute for Artificial Intelligence, Peking University（人工智能学院，北京大学）； Yuanpei College, Peking University（元培学院，北京大学）； State Key Laboratory of General Artificial Intelligence, BIGAI（通用人工智能国家重点实验室，BIGAI）

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

2504.16331 2025-09-29 cs.SE cs.LG 62%

Can Code Language Models Learn Clarification-Seeking Behaviors?

Jie JW Wu, Manav Chaudhary, Davit Abrahamyan, Arhaan Khaku, Anjiang Wei, Fatemeh H. Fard

机构 * Michigan Technological University（密歇根技术大学）； Indian Institute of Information Technology (IIIT)（印度信息科技研究所）； University of California, San Diego (UCSD)（加州大学圣地亚哥分校）； University of British Columbia（不列颠哥伦比亚大学）； Stanford University（斯坦福大学）

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

2509.20426 2025-09-26 cs.PL cs.SE 62%

Dual-Language General-Purpose Self-Hosted Visual Language and new Textual Programming Language for Applications

Mahmoud Samir Fayed

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

Comments PhD thesis

2509.18158 2025-09-26 cs.CL cs.LG 62%

ZERA: Zero-init Instruction Evolving Refinement Agent -- From Zero Instructions to Structured Prompts via Principle-based Optimization

Seungyoun Yi, Minsoo Khang, Sungrae Park

机构 * Upstage AI Research（Upstage人工智能研究院）

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

Comments 9 pages, 4 figures. To appear in EMNLP 2025 Main Conference (Oral Presentation)

2509.15754 2025-09-25 cs.CR cs.PL cs.SE 62%

Hornet Node and the Hornet DSL: A Minimal, Executable Specification for Bitcoin Consensus

Toby Sharp

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

2509.17070 2025-09-23 cs.CR cs.CL cs.LG 62%

Localizing Malicious Outputs from CodeLLM

Mayukh Borana, Junyi Liang, Sai Sathiesh Rajan, Sudipta Chattopadhyay

机构 * Singapore University of Technology and Design（新加坡科技设计大学）

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

Comments 10 pages, 2 figures, 6 tables, Accepted at EMNLP 2025 Findings

2501.08406 2025-09-23 cs.HC cs.CL cs.LG math.OC 62%

OptiChat: Bridging Optimization Models and Practitioners with Large Language Models

Hao Chen, Gonzalo Esteban Constante-Flores, Krishna Sri Ipsit Mantri, Sai Madhukiran Kompalli, Akshdeep Singh Ahluwalia, Can Li

机构 * Davidson School of Chemical Engineering（大卫逊化学工程学院）； Purdue University（普渡大学）

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

2509.13755 2025-09-18 cs.SE cs.AI cs.CR 62%

Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning

Zhaoyang Chu, Yao Wan, Zhikun Zhang, Di Wang, Zhou Yang, Hongyu Zhang, Pan Zhou, Xuanhua Shi, Hai Jin, David Lo

机构 * Huazhong University of Science and Technology（华中科技大学）； Zhejiang University（浙江大学）； King Abdullah University of Science and Technology（国王阿卜杜勒阿齐兹大学）； University of Alberta（阿尔伯塔大学）； Chongqing University（重庆大学）； Singapore Management University（新加坡管理学院）

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

Comments Accepted at the 48th IEEE/ACM International Conference on Software Engineering (ICSE 2026)

2509.12937 2025-09-17 cs.CR cs.AI cs.CL 62%

Jailbreaking Large Language Models Through Content Concretization

Johan Wahréus, Ahmed Hussain, Panos Papadimitratos

机构 * Networked Systems Security (NSS) Group（网络系统安全组）； KTH Royal Institute of Technology（皇家理工学院）

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

Comments Accepted for presentation in the Conference on Game Theory and AI for Security (GameSec) 2025

2411.03562 2025-09-16 cs.LG cs.AI 62%

Kolb-Based Experiential Learning for Generalist Agents with Human-Level Kaggle Data Science Performance

Antoine Grosnit, Alexandre Maraval, Refinath S N, Zichao Zhao, James Doran, Giuseppe Paolo, Albert Thomas, Jonas Gonzalez, Abhineet Kumar, Khyati Khandelwal, Abdelhakim Benechehab, Hamza Cherkaoui, Youssef Attia El-Hili, Kun Shao, Jianye Hao, Jun Yao, Balázs Kégl, Haitham Bou-Ammar, Jun Wang

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

2509.10946 2025-09-16 cs.SE cs.AI 62%

When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning

Roberto Morabito, Guanghan Wu

机构 * University of Helsinki（赫尔辛基大学）

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

Comments This paper has been accepted for publication in Computer (IEEE). Upon publication, the copyright will be transferred to IEEE

2503.23231 2025-09-16 cs.SE cs.AI 62%

CCCI: Code Completion with Contextual Information for Complex Data Transfer Tasks Using Large Language Models

Hangzhan Jin, Mohammad Hamdaqa

机构 * PolyTechnique Montréal（蒙特利尔理工学院）

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

Comments The 29th International Conference on Evaluation and Assessment in Software Engineering

Journal ref The 29th International Conference on Evaluation and Assessment in Software Engineering (EASE 2025)

2509.10099 2025-09-15 cs.SE cs.AI 62%

Generating Energy-Efficient Code via Large-Language Models -- Where are we now?

Radu Apsan, Vincenzo Stoico, Michel Albonico, Rudra Dhar, Karthik Vaidhyanathan, Ivano Malavolta

机构 * Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）； Federal University of Technology of Paraná (UTFPR)（巴西南里尔联邦技术大学）； IIIT Hyderabad（海得拉巴国家理工学院）

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

2509.09707 2025-09-15 cs.NE cs.AI cs.CL 62%

LLM-Based Instance-Driven Heuristic Bias In the Context of a Biased Random Key Genetic Algorithm

Camilo Chacón Sartori, Martín Isla Pino, Pedro Pinacho-Davidson, Christian Blum

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

Comments Submitted to a journal for review

2502.07128 2025-09-10 cs.CL cs.AI cs.MM 62%

Cardiverse: Harnessing LLMs for Novel Card Game Prototyping

Danrui Li, Sen Zhang, Sam S. Sohn, Kaidong Hu, Muhammad Usman, Mubbasir Kapadia

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

Comments 37 pages, 13 figures, 8 tables. Accepted by EMNLP 2025

2508.19268 2025-09-09 cs.CL cs.AI 62%

MultiPL-MoE: Multi-Programming-Lingual Extension of Large Language Models through Hybrid Mixture-of-Experts

Qing Wang, Xue Han, Jiahui Wang, Lehao Xing, Qian Hu, Lianlian Zhang, Chao Deng, Junlan Feng

机构 * China Mobile Research Institute（中国移动研究院）

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

2502.18658 2025-09-09 cs.HC cs.AI cs.SE 62%

Assistance or Disruption? Exploring and Evaluating the Design and Trade-offs of Proactive AI Programming Support

Kevin Pu, Daniel Lazaro, Ian Arawjo, Haijun Xia, Ziang Xiao, Tovi Grossman, Yan Chen

机构 * University of Toronto（多伦多大学）； University of California San Diego（加州大学圣地亚哥分校）； Johns Hopkins University（约翰霍普金斯大学）

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

2509.05160 2025-09-08 cs.PL cs.SE 62%

AI-Assisted Modeling: DSL-Driven AI Interactions

Steven Smyth, Daniel Busch, Moez Ben Haj Hmida, Edward A. Lee, Bernhard Steffen

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

Comments 7 pages, 4 figures

2502.09061 2025-09-08 cs.PL cs.LG 62%

CRANE: Reasoning with constrained LLM generation

Debangshu Banerjee, Tarun Suresh, Shubham Ugare, Sasa Misailovic, Gagandeep Singh

机构 * Department of Computer Science, University of Illinois Urbana-Champaign, USA（计算机科学系，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.LG、cs.PL

Comments Accepted at ICML 2025, Code at: https://github.com/uiuc-focal-lab/CRANE

1. 代码生成 4127 篇

Lang-PINN: From Language to Physics-Informed Neural Networks via a Multi-Agent Framework

Every Step Counts: Decoding Trajectories as Authorship Fingerprints of dLLMs

Finish First, Perfect Later: Test-Time Token-Level Cross-Validation for Diffusion Large Language Models

SALAD: Systematic Assessment of Machine Unlearning on LLM-Aided Hardware Design

Investigating The Smells of LLM Generated Code

Mechanistic Interpretability of Code Correctness in LLMs via Sparse Autoencoders

Modeling Others' Minds as Code

RiskPO: Risk-based Policy Optimization via Verifiable Reward for LLM Post-Training

Combining Large Language Models and Gradient-Free Optimization for Automatic Control Policy Synthesis

RFG: Test-Time Scaling for Diffusion Large Language Model Reasoning with Reward-Free Guidance

Memory Transfer Planning: LLM-driven Context-Aware Code Adaptation for Robot Manipulation

HD-PiSSA: High-Rank Distributed Orthogonal Adaptation

Can Code Language Models Learn Clarification-Seeking Behaviors?

Dual-Language General-Purpose Self-Hosted Visual Language and new Textual Programming Language for Applications

ZERA: Zero-init Instruction Evolving Refinement Agent -- From Zero Instructions to Structured Prompts via Principle-based Optimization

Hornet Node and the Hornet DSL: A Minimal, Executable Specification for Bitcoin Consensus

Localizing Malicious Outputs from CodeLLM

OptiChat: Bridging Optimization Models and Practitioners with Large Language Models

Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning

Jailbreaking Large Language Models Through Content Concretization

Kolb-Based Experiential Learning for Generalist Agents with Human-Level Kaggle Data Science Performance

When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning

CCCI: Code Completion with Contextual Information for Complex Data Transfer Tasks Using Large Language Models

Generating Energy-Efficient Code via Large-Language Models -- Where are we now?

LLM-Based Instance-Driven Heuristic Bias In the Context of a Biased Random Key Genetic Algorithm

Cardiverse: Harnessing LLMs for Novel Card Game Prototyping

MultiPL-MoE: Multi-Programming-Lingual Extension of Large Language Models through Hybrid Mixture-of-Experts

Assistance or Disruption? Exploring and Evaluating the Design and Trade-offs of Proactive AI Programming Support

AI-Assisted Modeling: DSL-Driven AI Interactions

CRANE: Reasoning with constrained LLM generation