代码大模型 / AI 编程

Re-ReST: Reflection-Reinforced Self-Training for Language Agents

Zi-Yi Dou, Cheng-Fu Yang, Xueqing Wu, Kai-Wei Chang, Nanyun Peng

机构 * University of California, Los Angeles（加州大学洛杉矶分校） 纠错

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

STORY2GAME: Generating (Almost) Everything in an Interactive Fiction Game

Eric Zhou, Shreyas Basavatia, Moontashir Siam, Zexin Chen, Mark O. Riedl

机构 * School of Interactive Computing, College of Computing（交互计算学院、计算机学院） 纠错

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

PipeSpec: Breaking Stage Dependencies in Hierarchical LLM Decoding

Bradley McDanel, Sai Qian Zhang, Yunhai Hu, Zining Liu

机构 * Franklin and Marshall College（弗兰克林与马歇尔学院） ； New York University（纽约大学） ； University of Pennsylvania（宾夕法尼亚大学） 纠错

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

Comments 10 pages, 5 figures, 2 tables

Towards Optimal Circuit Generation: Multi-Agent Collaboration Meets Collective Intelligence

Haiyan Qin, Jiahao Feng, Xiaotong Feng, Wei W. Xing, Wang Kang

机构 * National Key Laboratory of Spintronics, Hangzhou International Innovation Institute（国家磁电子键实验室、杭州国际创新研究院；集成电路科学与工程学院，北京航空航天大学） ； School of Integrated Circuit Science and Engineering, Beihang University（机械电子工程学院，武汉理工大学） ； School of Mechanical and Electronic Engineering, Wuhan University of Technology（数学与物理科学学院，谢菲尔德大学） ； School of Mathematical and Physical Sciences, University of Sheffield 纠错

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

Comments 9 pages, 6 figures

Guided Tensor Lifting

Yixuan Li, José Wesley de Souza Magalhães, Alexander Brauckmann, Michael F. P. O'Boyle, Elizabeth Polgreen

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

Comments PLDI 2025 main conference

The Role of Generative AI in Strengthening Secure Software Coding Practices: A Systematic Perspective

Hathal S. Alwageed, Rafiq Ahmad Khan

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

Comments 1-6 pages

"I Would Have Written My Code Differently'': Beginners Struggle to Understand LLM-Generated Code

Yangtian Zi, Luisa Li, Arjun Guha, Carolyn Jane Anderson, Molly Q Feldman

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

Comments To appear in 33rd ACM International Conference on the Foundations of Software Engineering (FSE Companion '25), June 23-28, 2025, Trondheim, Norway

Multimodal graph representation learning for website generation based on visual sketch

Tung D. Vu, Chung Hoang, Truong-Son Hy

机构 * College of Engineering and Computer Science（工程与计算机科学学院） ； VinUniversity Hanoi（河内 Vin 大学） ； Department of Computer Science（计算机科学系） ； Hanoi University of Science and Technology（河内科学技术大学） ； The University of Alabama at Birmingham（阿拉巴马大学伯明翰分校） 纠错

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

MSCoT: Structured Chain-of-Thought Generation for Multiple Programming Languages

Naizhu Jin, Zhong Li, Tian Zhang, Qingkai Zeng

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

Comments accepted in ijcnn 2025

Insights from Verification: Training a Verilog Generation LLM with Reinforcement Learning with Testbench Feedback

Ning Wang, Bingkun Yao, Jie Zhou, Yuchen Hu, Xi Wang, Nan Guan, Zhe Jiang

机构 * City University of Hong Kong（香港城市大学） ； Southeast University（东南大学） 纠错

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

Quantifying the benefits of code hints for refactoring deprecated Java APIs

Cristina David, Pascal Kesseli, Daniel Kroening, Hanliang Zhang

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

Journal ref 33rd ACM International Conference on the Foundations of Software Engineering (FSE Companion '25), June 23--28, 2025, Trondheim, Norway

MaCTG: Multi-Agent Collaborative Thought Graph for Automatic Programming

Zixiao Zhao, Jing Sun, Zhe Hou, Zhiyuan Wei, Cheng-Hao Cai, Miao Qiao, Jin Song Dong

机构 * School of Computer Science, University of Auckland（计算机科学系，奥克兰大学） ； School of Information and Communication Technology, Griffith University（信息与通信技术系，格里菲斯大学） ； Beijing Institute of Technology（北京理工大学） ； Suzhou Industrial Park Monash Research Institute of Science and Technology（苏州工业园区莫纳什科学与技术研究所） ； School of Computing, National University of Singapore（计算系，新加坡国立大学） 纠错

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

MCGMark: An Encodable and Robust Online Watermark for Tracing LLM-Generated Malicious Code

Kaiwen Ning, Jiachi Chen, Qingyuan Zhong, Tao Zhang, Yanlin Wang, Wei Li, Jingwen Zhang, Jianxing Yu, Yuming Feng, Weizhe Zhang, Zibin Zheng

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

Large Language Model for Verilog Generation with Code-Structure-Guided Reinforcement Learning

Ning Wang, Bingkun Yao, Jie Zhou, Xi Wang, Zhe Jiang, Nan Guan

机构 * City University of Hong Kong（香港城市大学） ； Southeast University（东南大学） 纠错

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

Towards End-to-End Network Intent Management with Large Language Models

Lam Dinh, Sihem Cherrared, Xiaofeng Huang, Fabrice Guillemin

机构 * Orange Innovation（Orange创新） 纠错

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

Comments Full paper is accepted at IFIP Networking 2025

Chinese-Vicuna: A Chinese Instruction-following Llama-based Model

Chenghao Fan, Zhenyi Lu, Jie Tian

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

Comments Chinese-Vicuna Technique Report

Rethinking the Generation of High-Quality CoT Data from the Perspective of LLM-Adaptive Question Difficulty Grading

Qianjin Yu, Keyu Wu, Zihan Chen, Chushu Zhang, Manlin Mei, Lingjun Huang, Fang Tan, Yongsheng Du, Kunlin Liu, Yurui Zhu

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

MDIT: A Model-free Data Interpolation Method for Diverse Instruction Tuning

Yangning Li, Zihua Lan, Lv Qingsong, Yinghui Li, Hai-Tao Zheng

机构 * Tsinghua University（清华大学） 纠错

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

TinyverseGP: Towards a Modular Cross-domain Benchmarking Framework for Genetic Programming

Roman Kalkreuth, Fabricio Olivetti de França, Julian Dierkes, Marie Anastacio, Anja Jankovic, Zdenek Vasicek, Holger Hoos

机构 * RWTH Aachen University（亚琛工业大学） ； Brno University of Technology（布尔诺理工大学） 纠错

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

Comments Accepted for presentation as a poster at the Genetic and Evolutionary Computation Conference (GECCO) and will appear in the GECCO'25 companion. GECCO'25 will be held July 14-18, 2025 in Málaga, Spain

Journal ref GECCO'25 Companion: Genetic and Evolutionary Computation Conference Companion, July 14-18, 2025, Malaga, Spain

ClassEval-T: Evaluating Large Language Models in Class-Level Code Translation

Pengyu Xue, Linhao Wu, Zhen Yang, Chengyi Wang, Xiang Li, Yuxiang Zhang, Jia Li, Ruikai Jin, Yifei Pei, Zhaoyan Shen, Xiran Lyu, Jacky Wai Keung

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

Boosting Universal LLM Reward Design through Heuristic Reward Observation Space Evolution

Zen Kit Heng, Zimeng Zhao, Tianhao Wu, Yuanfei Wang, Mingdong Wu, Yangang Wang, Hao Dong

机构 * Center on Frontiers of Computing Studies, School of Computer Science, Peking University（北京大学计算机学院计算前沿研究中心） ； PKU-Agibot Lab, School of Computer Science, Peking University（北京大学计算机学院PKU-Agibot实验室） ； National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University（北京大学计算机学院多媒体信息处理国家重点实验室） ； School of Automation, Southeast University（东南大学自动化学院） 纠错

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

Comments 7 pages, 5 figures

GSCE: A Prompt Framework with Enhanced Reasoning for Reliable LLM-driven Drone Control

Wenhao Wang, Yanyan Li, Long Jiao, Jiawei Yuan

机构 * University of Massachusetts Dartmouth（马萨诸塞大学达特茅斯分校） ； California State University San Marcos（加州州立大学圣马科斯分校） 纠错

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

Comments 8 pages

The Self-Learning Agent with a Progressive Neural Network Integrated Transformer

Ajay Sivakumar, Shalini, Vasantha Raj, Sebastian Sylvester

机构 * Hindustan Institute of Technology and Science（印度斯坦理工学院） 纠错

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

Comments 7 pages, 2 figures, focuses on continual learning with PNN and LLaMA. Experiments demonstrate scalability and lifelong learning capabilities

How Difficulty-Aware Staged Reinforcement Learning Enhances LLMs' Reasoning Capabilities: A Preliminary Experimental Study

Yunjie Ji, Sitong Zhao, Xiaoyu Tian, Haotian Wang, Shuaiting Chen, Yiping Peng, Han Zhao, Xiangang Li

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

LaMOuR: Leveraging Language Models for Out-of-Distribution Recovery in Reinforcement Learning

Chan Kim, Seung-Woo Seo, Seong-Woo Kim

机构 * Seoul National University（首尔大学） 纠错

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

Comments 14 pages, 16 figures

SLA-Awareness for AI-assisted coding

Kishanthan Thangarajah, Arthur Leung, Boyuan Chen, Ahmed E. Hassan

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

SpecEval: Evaluating Code Comprehension in Large Language Models via Program Specifications

Lezhi Ma, Shangqing Liu, Lei Bu, Shangru Li, Yida Wang, Yang Liu

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

A new approach for encoding code and assisting code understanding

Mengdan Fan, Wei Zhang, Haiyan Zhao, Zhi Jin

机构 * Peking University（北京大学） 纠错

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

Comments 10 page, 14 figures

Automated Harmfulness Testing for Code Large Language Models

Honghao Tan, Haibo Wang, Diany Pressato, Yisen Xu, Shin Hwei Tan

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

SENAI: Towards Software Engineering Native Generative Artificial Intelligence

Mootez Saad, José Antonio Hernández López, Boqi Chen, Neil Ernst, Dániel Varró, Tushar Sharma

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

Comments 5 pages, 1 figure