代码大模型 / AI 编程

Writing-Zero: Bridge the Gap Between Non-verifiable Tasks and Verifiable Rewards

Ruipeng Jia, Yunyi Yang, Yongbo Gai, Kai Luo, Shihao Huang, Jianhe Lin, Xiaoxi Jiang, Guanjun Jiang

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

PDE-Controller: LLMs for Autoformalization and Reasoning of PDEs

Mauricio Soroco, Jialin Song, Mengzhou Xia, Kye Emond, Weiran Sun, Wuyang Chen

机构 * Princeton University（普林斯顿大学） ； Simon Fraser University（西蒙弗雷泽大学） ； School of Computing Science, Simon Fraser University（西蒙弗雷泽大学计算科学学院） 纠错

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

Cross-lingual Transfer in Programming Languages: An Extensive Empirical Study

Razan Baltaji, Saurabh Pujar, Louis Mandel, Martin Hirzel, Luca Buratti, Lav Varshney

机构 * Department of Electrical and Computer Engineering（电气与计算机工程系） ； University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； IBM Research（IBM研究院） 纠错

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

Comments Published in Transactions on Machine Learning Research (06/2025) 26 pages, 5 figures, 10 tables

TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts

Torsten Krauß, Hamid Dashtbani, Alexandra Dmitrienko

机构 * University of Würzburg（乌尔姆大学） 纠错

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

Comments 26 pages, 25 tables, 13 figures, 2 algorithms, to appear in the 43th USENIX Security Symposium (USENIX Security 2025)

KnowCoder-V2: Deep Knowledge Analysis

Zixuan Li, Wenxuan Liu, Long Bai, Chunmao Zhang, Wei Li, Fenghui Zhang, Quanxin Jin, Ruoyun He, Zhuo Chen, Zhilei Hu, Fei Wang, Bingbing Xu, Xuhui Jiang, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

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

Which Prompting Technique Should I Use? An Empirical Investigation of Prompting Techniques for Software Engineering Tasks

E. G. Santana, Gabriel Benjamin, Melissa Araujo, Harrison Santos, David Freitas, Eduardo Almeida, Paulo Anselmo da M. S. Neto, Jiawei Li, Jina Chun, Iftekhar Ahmed

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

Demonstrations of Integrity Attacks in Multi-Agent Systems

Can Zheng, Yuhan Cao, Xiaoning Dong, Tianxing He

机构 * Shanghai Qi Zhi Institute（上海启智研究院） ； Institute for Interdisciplinary Information Sciences, Tsinghua University（清华大学交叉信息研究院） ； University of Pittsburgh（匹兹堡大学） ； ShanghaiTech University（上海科技大学） 纠错

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

Computational Thinking Reasoning in Large Language Models

Kechi Zhang, Ge Li, Jia Li, Huangzhao Zhang, Jingjing Xu, Hao Zhu, Lecheng Wang, Jia Li, Yihong Dong, Jing Mai, Bin Gu, Zhi Jin

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

Improving LLM-Generated Code Quality with GRPO

Maxime Robeyns, Laurence Aitchison

机构 * University of Bristol（布里斯托大学） 纠错

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

DATCloud: A Model-Driven Framework for Multi-Layered Data-Intensive Architectures

Moamin Abughazala, Henry Muccini

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

A "Wenlu" Brain System for Multimodal Cognition and Embodied Decision-Making: A Secure New Architecture for Deep Integration of Foundation Models and Domain Knowledge

Liang Geng

机构 * College of Mechanical and Electrical Engineering, Shijiazhuang University（石家庄大学机械与电气工程学院） ； School of Artificial Intelligence, Beijing University of Posts and Telecommunications（北京邮电大学人工智能学院） ； The Key Laboratory of Agricultural Robotics Intelligent Perception in Shijiazhuang（石家庄农业机器人智能感知重点实验室） 纠错

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

From Mathematical Reasoning to Code: Generalization of Process Reward Models in Test-Time Scaling

Zhengyu Chen, Yudong Wang, Teng Xiao, Ruochen Zhou, Xuesheng Yang, Wei Wang, Zhifang Sui, Jingang Wang

机构 * Meituan Inc.（美团公司） ； National Key Laboratory for Multimedia Information Processing, Peking University（北京大学多媒体信息处理国家重点实验室） ； Pennsylvania State University（宾夕法尼亚大学） 纠错

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

RMoA: Optimizing Mixture-of-Agents through Diversity Maximization and Residual Compensation

Zhentao Xie, Chengcheng Han, Jinxin Shi, Wenjun Cui, Xin Zhao, Xingjiao Wu, Jiabao Zhao

机构 * East China Normal University（华东师范大学） ； Meituan Inc.（美团公司） ； Donghua University（东华大学） ； Tsinghua University（清华大学） 纠错

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

Comments Accepted by ACL 2025 (Findings)

A Reward-driven Automated Webshell Malicious-code Generator for Red-teaming

Yizhong Ding

机构 * Beijing Electronic Science and Technology Institute（北京电子科技学院） 纠错

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

Krikri: Advancing Open Large Language Models for Greek

Dimitris Roussis, Leon Voukoutis, Georgios Paraskevopoulos, Sokratis Sofianopoulos, Prokopis Prokopidis, Vassilis Papavasileiou, Athanasios Katsamanis, Stelios Piperidis, Vassilis Katsouros

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

Infinite-Instruct: Synthesizing Scaling Code instruction Data with Bidirectional Synthesis and Static Verification

Wenjing Xing, Wenke Lu, Yeheng Duan, Bing Zhao, Zhenghui kang, Yaolong Wang, Kai Gao, Lei Qiao

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

The Power of Personality: A Human Simulation Perspective to Investigate Large Language Model Agents

Yifan Duan, Yihong Tang, Xuefeng Bai, Kehai Chen, Juntao Li, Min Zhang

机构 * Institute of Computing and Intelligence, Harbin Institute of Technology, Shenzhen, China（计算与智能研究院，哈尔滨工业大学深圳校区） 纠错

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

FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflow

Haoyu Sun, Huichen Will Wang, Jiawei Gu, Linjie Li, Yu Cheng

机构 * Tongji University（同济大学） ； University of Washington（华盛顿大学） ； Sun Yat-sen University（中山大学） ； Microsoft（微软） ； The Chinese University of Hong Kong（香港中文大学） 纠错

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

In-the-loop Hyper-Parameter Optimization for LLM-Based Automated Design of Heuristics

Niki van Stein, Diederick Vermetten, Thomas Bäck

机构 * LIACS, Leiden University（LIACS，莱顿大学） 纠错

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

RAG or Fine-tuning? A Comparative Study on LCMs-based Code Completion in Industry

Chaozheng Wang, Zezhou Yang, Shuzheng Gao, Cuiyun Gao, Ting Peng, Hailiang Huang, Yuetang Deng, Michael Lyu

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

Comments Accepted in FSE 25 Industry Track

Capturing the Effects of Quantization on Trojans in Code LLMs

Aftab Hussain, Sadegh AlMahdi Kazemi Zarkouei, Md Rafiqul Islam Rabin, Mohammad Amin Alipour, Sen Lin, Bowen Xu

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

LongDPO: Unlock Better Long-form Generation Abilities for LLMs via Critique-augmented Stepwise Information

Bowen Ping, Jiali Zeng, Fandong Meng, Shuo Wang, Jie Zhou, Shanghang Zhang

机构 * State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University（多媒体信息处理国家重点实验室，计算机科学学院，北京大学） ； Pattern Recongnition Center, WechatAI, Tencent Inc（图案识别中心，微信AI，腾讯公司） ； Dept. of Comp. Sci. & Tech., Tsinghua University（计算机科学与技术系，清华大学） 纠错

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

Comments ACL 2025

RN-F: A Novel Approach for Mitigating Contaminated Data in Large Language Models

Le Vu Anh, Dinh Duc Nha Nguyen, Phi Long Nguyen

机构 * TinyAI Research（TinyAI研究所） ； Center for Environmental Intelligence（环境智能中心） ； College of Engineering & Computer Science（工程与计算机科学学院） 纠错

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

Comments 12 pages, 4 figures, 3 tables

Goals as Reward-Producing Programs

Guy Davidson, Graham Todd, Julian Togelius, Todd M. Gureckis, Brenden M. Lake

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

Comments Project website and goal program viewer: https://exps.gureckislab.org/guydav/goal_programs_viewer/main/

Code Retrieval for MILP Instance Generation

Tianxing Yang, Huigen Ye, Hua Xu

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

Code-Driven Planning in Grid Worlds with Large Language Models

Ashwath Vaithinathan Aravindan, Zhisheng Tang, Mayank Kejriwal

机构 * University of Southern California（南加州大学） ； University of Southern California Information Sciences Institute（南加州大学信息科学研究所） 纠错

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

Can You Really Trust Code Copilots? Evaluating Large Language Models from a Code Security Perspective

Yutao Mou, Xiao Deng, Yuxiao Luo, Shikun Zhang, Wei Ye

机构 * National Engineering Research Center for Software Engineering, Peking University, China（软件工程国家工程研究中心，北京大学） 纠错

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

Comments Accepted by ACL2025 Main Conference

Qwen3 Technical Report

An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jing Zhou, Jingren Zhou, Junyang Lin, Kai Dang, Keqin Bao, Kexin Yang, Le Yu, Lianghao Deng, Mei Li, Mingfeng Xue, Mingze Li, Pei Zhang, Peng Wang, Qin Zhu, Rui Men, Ruize Gao, Shixuan Liu, Shuang Luo, Tianhao Li, Tianyi Tang, Wenbiao Yin, Xingzhang Ren, Xinyu Wang, Xinyu Zhang, Xuancheng Ren, Yang Fan, Yang Su, Yichang Zhang, Yinger Zhang, Yu Wan, Yuqiong Liu, Zekun Wang, Zeyu Cui, Zhenru Zhang, Zhipeng Zhou, Zihan Qiu

机构 * Qwen Team（通义实验室） 纠错

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

Agent-as-a-Service based on Agent Network

Yuhan Zhu, Haojie Liu, Jian Wang, Bing Li, Zikang Yin, Yefei Liao

机构 * School of Computer Science Wuhan University（武汉大学计算机学院） 纠错

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

Comments work in progress

Evaluating LLM Metrics Through Real-World Capabilities

Justin K Miller, Wenjia Tang

机构 * School of Physics University of Sydney（悉尼大学物理系） ； School of Art, Communication and English University of Sydney（悉尼大学艺术、传播与英语系） 纠错

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

Comments 14 pages main text, 5 pages references, 20 pages appendix; includes 3 figures and 4 tables