代码大模型 / AI 编程

Verifying LLM-Generated Code in the Context of Software Verification with Ada/SPARK

Marcos Cramer, Lucian McIntyre

机构 * secunet Security Networks AG（secunet安全网络股份公司） ； International Center for Computational Logic, Technical University Dresden（德累斯顿工业大学国际计算逻辑中心） 纠错

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

Reranking Laws for Language Generation: A Communication-Theoretic Perspective

António Farinhas, Haau-Sing Li, André F. T. Martins

机构 * Instituto Superior Técnico, Universidade de Lisboa（里斯本大学高等技术学院） ； Instituto de Telecomunicações（电信研究所） ； TU Darmstadt（达姆施塔特工业大学） ； ELLIS Unit Lisbon（欧洲卓越学习系统里斯本单元） ； Unbabel（昂巴贝尔公司） 纠错

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

Comments NeurIPS 2024 (spotlight)

Beyond Autoregression: Fast LLMs via Self-Distillation Through Time

Justin Deschenaux, Caglar Gulcehre

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

Logic-Q: Improving Deep Reinforcement Learning-based Quantitative Trading via Program Sketch-based Tuning

Zhiming Li, Junzhe Jiang, Yushi Cao, Aixin Cui, Bozhi Wu, Bo Li, Yang Liu, Danny Dongning Sun

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

Comments accepted by AAAI 2025

Analysis of LLMs vs Human Experts in Requirements Engineering

Cory Hymel, Hiroe Johnson

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

Comments 8 pages, 15 figures

If You Can't Use Them, Recycle Them: Optimizing Merging at Scale Mitigates Performance Tradeoffs

Muhammad Khalifa, Yi-Chern Tan, Arash Ahmadian, Tom Hosking, Honglak Lee, Lu Wang, Ahmet Üstün, Tom Sherborne, Matthias Gallé

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

Comments 13 pages, 9 figures

PlotGen: Multi-Agent LLM-based Scientific Data Visualization via Multimodal Feedback

Kanika Goswami, Puneet Mathur, Ryan Rossi, Franck Dernoncourt

机构 * Adobe Research（奥多比研究院） 纠错

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

From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation

Xingchen Wan, Han Zhou, Ruoxi Sun, Hootan Nakhost, Ke Jiang, Sercan Ö. Arık

机构 * Google Cloud AI Research（谷歌云AI研究院） 纠错

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

Comments Expanded version of the ICLR 2025 paper

Enhancing Large Language Model Efficiencyvia Symbolic Compression: A Formal Approach Towards Interpretability

Lumen AI, Tengzhou No. 1 Middle School, Shihao Ji, Zihui Song, Fucheng Zhong, Jisen Jia, Zhaobo Wu, Zheyi Cao, Tianhao Xu

机构 * Lumen AI（卢门人工智能公司） ； Tengzhou No. 1 Middle School（滕州市第一中学） 纠错

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

Compositional Hardness of Code in Large Language Models -- A Probabilistic Perspective

Yotam Wolf, Binyamin Rothberg, Dorin Shteyman, Amnon Shashua

机构 * The Hebrew University（希伯来大学） 纠错

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

Turbulence: Systematically and Automatically Testing Instruction-Tuned Large Language Models for Code

Shahin Honarvar, Mark van der Wilk, Alastair Donaldson

机构 * Imperial College London（伦敦帝国学院） ； University of Oxford（牛津大学） 纠错

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

Comments Updated to the ICST2025 conference version

ARCEAK: An Automated Rule Checking Framework Enhanced with Architectural Knowledge

Junyong Chen, Ling-I Wu, Minyu Chen, Xiaoying Qian, Haoze Zhu, Qiongfang Zhang, Guoqiang Li

机构 * Shanghai Jiao Tong University（上海交通大学） ； Beijing University of Civil Engineering and Architecture（北京建筑大学） ； East China Architectural Design & Research Institute（华东建筑设计研究院） 纠错

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

Comments 12 pages, 5 figures

Beyond the Sum: Unlocking AI Agents Potential Through Market Forces

Jordi Montes Sanabria, Pol Alvarez Vecino

机构 * Fewsats 纠错

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

Comments 20 pages, 5 figures

Pseudocode-Injection Magic: Enabling LLMs to Tackle Graph Computational Tasks

Chang Gong, Wanrui Bian, Zhijie Zhang, Weiguo Zheng

机构 * School of Data Science, Fudan University（复旦大学数据科学学院） 纠错

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

Comments 24 pages

CodeHalu: Investigating Code Hallucinations in LLMs via Execution-based Verification

Yuchen Tian, Weixiang Yan, Qian Yang, Xuandong Zhao, Qian Chen, Wen Wang, Ziyang Luo, Lei Ma, Dawn Song

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

Comments Accepted by AAAI 2025 main conference

SYNAPSE: SYmbolic Neural-Aided Preference Synthesis Engine

Sadanand Modak, Noah Patton, Isil Dillig, Joydeep Biswas

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

Comments Accepted (oral) at AAAI 25

Practical Design and Benchmarking of Generative AI Applications for Surgical Billing and Coding

John C. Rollman, Bruce Rogers, Hamed Zaribafzadeh, Daniel Buckland, Ursula Rogers, Jennifer Gagnon, Ozanan Meireles, Lindsay Jennings, Jim Bennett, Jennifer Nicholson, Nandan Lad, Linda Cendales, Andreas Seas, Alessandro Martinino, E. Shelley Hwang, Allan D. Kirk

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

Comments 21 pages, 3 figures, 2 tables

RTLSquad: Multi-Agent Based Interpretable RTL Design

Bowei Wang, Qi Xiong, Zeqing Xiang, Lei Wang, Renzhi Chen

机构 * National University of Defense Technology（国防科技大学） ； Intelligent Microelectronics Center（智能微电子中心） ； Qiyuan Lab（启元实验室） ； Defense Innovation Institute（国防创新研究院） ； Academy of Military Science（军事科学院） 纠错

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

Do Code LLMs Understand Design Patterns?

Zhenyu Pan, Xuefeng Song, Yunkun Wang, Rongyu Cao, Binhua Li, Yongbin Li, Han Liu

机构 * Northwestern University（西北大学） ； Zhejiang University（浙江大学） ； Alibaba Group（阿里巴巴集团） 纠错

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

Comments accpeted by llm4code workshop in ICSE 2025

ChronoLLM: A Framework for Customizing Large Language Model for Digital Twins generalization based on PyChrono

Jingquan Wang, Harry Zhang, Khailanii Slaton, Shu Wang, Radu Serban, Jinlong Wu, Dan Negrut

机构 * UW-Madison（威斯康星大学麦迪逊分校） 纠错

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

CodeVision: Detecting LLM-Generated Code Using 2D Token Probability Maps and Vision Models

Zhenyu Xu, Victor S. Sheng

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

Seed-CTS: Unleashing the Power of Tree Search for Superior Performance in Competitive Coding Tasks

Hao Wang, Boyi Liu, Yufeng Zhang, Jie Chen

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

M-Ped: Multi-Prompt Ensemble Decoding for Large Language Models

Jiaxin Guo, Daimeng Wei, Yuanchang Luo, Shimin Tao, Hengchao Shang, Zongyao Li, Shaojun Li, Jinlong Yang, Zhanglin Wu, Zhiqiang Rao, Hao Yang

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

HPC-Coder-V2: Studying Code LLMs Across Low-Resource Parallel Languages

Aman Chaturvedi, Daniel Nichols, Siddharth Singh, Abhinav Bhatele

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

Tree-of-Code: A Hybrid Approach for Robust Complex Task Planning and Execution

Ziyi Ni, Yifan Li, Daxiang Dong

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

Comments Submitted to the Neurips Workshop "System 2 Reasoning" in September, 2024. The openreview is avaliable at https://openreview.net/forum?id=8NKAL8Ngxk

An Exploratory Study of ML Sketches and Visual Code Assistants

Luís F. Gomes, Vincent J. Hellendoorn, Jonathan Aldrich, Rui Abreu

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

Journal ref Proceedings of the 2025 IEEE/ACM 47th International Conference on Software Engineering (ICSE)

DialogAgent: An Auto-engagement Agent for Code Question Answering Data Production

Xiaoyun Liang, Jingyi Ren, Jiayi Qi, Chao Peng, Bo Jiang

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

How secure is AI-generated Code: A Large-Scale Comparison of Large Language Models

Norbert Tihanyi, Tamas Bisztray, Mohamed Amine Ferrag, Ridhi Jain, Lucas C. Cordeiro

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

Comments Accepted and will be shortly published at Empirical Software Engineering (EMSE). Journal Impact Factor: 3.5 (2023)

Copyright-Protected Language Generation via Adaptive Model Fusion

Javier Abad, Konstantin Donhauser, Francesco Pinto, Fanny Yang

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

Comments 47 pages, 21 Figures. arXiv admin note: substantial text overlap with arXiv:2407.20105

Enhancing Cross-Language Code Translation via Task-Specific Embedding Alignment in Retrieval-Augmented Generation

Manish Bhattarai, Minh Vu, Javier E. Santos, Ismael Boureima, Daniel O' Malley

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