代码大模型 / AI 编程

Investigating the Effectiveness of a Socratic Chain-of-Thoughts Reasoning Method for Task Planning in Robotics, A Case Study

Veronica Bot, Zheyuan Xu

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

An Empirical Comparison of Cost Functions in Inductive Logic Programming

Céline Hocquette, Andrew Cropper

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

Bias Unveiled: Investigating Social Bias in LLM-Generated Code

Lin Ling, Fazle Rabbi, Song Wang, Jinqiu Yang

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

Comments accepted for publication in the Association for the Advancement of Artificial Intelligence (AAAI), 2025

From Code to Courtroom: LLMs as the New Software Judges

Junda He, Jieke Shi, Terry Yue Zhuo, Christoph Treude, Jiamou Sun, Zhenchang Xing, Xiaoning Du, David Lo

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

CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking

Tarun Suresh, Revanth Gangi Reddy, Yifei Xu, Zach Nussbaum, Andriy Mulyar, Brandon Duderstadt, Heng Ji

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

Comments Published as a conference paper at ICLR 2025. First and second author had equal contribution

AI Agents for Ground-Based Gamma Astronomy

D. Kostunin, V. Sotnikov, S. Golovachev, A. Strube

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

Comments proceedings of ADASS2025 (submitted), original talk and demos: https://pretalx.com/adass2024/talk/TRFZKU/

LLMs are everywhere: Ubiquitous Utilization of AI Models through Air Computing

Baris Yamansavascilar, Atay Ozgovde, Cem Ersoy

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

Comments 7 pages, 5 figures

Steering Large Language Models between Code Execution and Textual Reasoning

Yongchao Chen, Harsh Jhamtani, Srinagesh Sharma, Chuchu Fan, Chi Wang

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

Comments 32 pages, 12 figures, 12 tables

Journal ref The Thirteenth International Conference on Learning Representations (ICLR'2025)

Dynamics of Instruction Fine-Tuning for Chinese Large Language Models

Chiyu Song, Zhanchao Zhou, Jianhao Yan, Yuejiao Fei, Zhenzhong Lan, Yue Zhang

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

Comments Accepted to COLING 2025

Procedural Synthesis of Synthesizable Molecules

Michael Sun, Alston Lo, Minghao Guo, Jie Chen, Connor Coley, Wojciech Matusik

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

Comments ICLR 2025

GUIDE: LLM-Driven GUI Generation Decomposition for Automated Prototyping

Kristian Kolthoff, Felix Kretzer, Christian Bartelt, Alexander Maedche, Simone Paolo Ponzetto

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

Generating CAD Code with Vision-Language Models for 3D Designs

Kamel Alrashedy, Pradyumna Tambwekar, Zulfiqar Zaidi, Megan Langwasser, Wei Xu, Matthew Gombolay

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

AI's Impact on Traditional Software Development

Bhanuprakash Madupati

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

Comments 10 Pages , 5 figures

Journal ref Journal of Artificial Intelligence & Cloud Computing , Published Date: 2024-07-24

How Scientists Use Large Language Models to Program

Gabrielle O'Brien

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

Comments Accepted to CHI 2025

Evaluating the Effectiveness and Efficiency of Demonstration Retrievers in RAG for Coding Tasks

Pengfei He, Shaowei Wang, Shaiful Chowdhury, Tse-Hsun Chen

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

Comments 11 pages, 6 figures, 6 tables, accepted by SANER 2025

An approach for API synthesis using large language models

Hua Zhong, Shan Jiang, Sarfraz Khurshid

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

GATE: Graph-based Adaptive Tool Evolution Across Diverse Tasks

Jianwen Luo, Yiming Huang, Jinxiang Meng, Fangyu Lei, Shizhu He, Xiao Liu, Shanshan Jiang, Bin Dong, Jun Zhao, Kang Liu

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

Comments 8 pages of main text, 38 pages of appendices

AutoParLLM: GNN-guided Context Generation for Zero-Shot Code Parallelization using LLMs

Quazi Ishtiaque Mahmud, Ali TehraniJamsaz, Hung Phan, Le Chen, Mihai Capotă, Theodore Willke, Nesreen K. Ahmed, Ali Jannesari

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

Uncovering the Impact of Chain-of-Thought Reasoning for Direct Preference Optimization: Lessons from Text-to-SQL

Hanbing Liu, Haoyang Li, Xiaokang Zhang, Ruotong Chen, Haiyong Xu, Tian Tian, Qi Qi, Jing Zhang

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

Enhancing Cross-Tokenizer Knowledge Distillation with Contextual Dynamical Mapping

Yijie Chen, Yijin Liu, Fandong Meng, Yufeng Chen, Jinan Xu, Jie Zhou

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

Comments The code is available at https://github.com/pppa2019/ContexualDynamicMapping

Can humans teach machines to code?

Céline Hocquette, Johannes Langer, Andrew Cropper, Ute Schmid

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

Self-Refinement Strategies for LLM-based Product Attribute Value Extraction

Alexander Brinkmann, Christian Bizer

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

Faster Language Models with Better Multi-Token Prediction Using Tensor Decomposition

Artem Basharin, Andrei Chertkov, Ivan Oseledets

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

Refining Integration-by-Parts Reduction of Feynman Integrals with Machine Learning

Matt von Hippel, Matthias Wilhelm

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

Comments 28 pages, 9 figures

nvAgent: Automated Data Visualization from Natural Language via Collaborative Agent Workflow

Geliang Ouyang, Jingyao Chen, Zhihe Nie, Yi Gui, Yao Wan, Hongyu Zhang, Dongping Chen

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

Learning Semantics-aware Search Operators for Genetic Programming

Piotr Wyrwiński, Krzysztof Krawiec

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

Comments Submitted to GECCO 2025

Security Weaknesses of Copilot-Generated Code in GitHub Projects: An Empirical Study

Yujia Fu, Peng Liang, Amjed Tahir, Zengyang Li, Mojtaba Shahin, Jiaxin Yu, Jinfu Chen

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

Comments Preprint accepted for publication in ACM Transactions on Software Engineering and Methodology (TOSEM), 2025

Resource-Efficient & Effective Code Summarization

Saima Afrin, Joseph Call, Khai-Nguyen Nguyen, Oscar Chaparro, Antonio Mastropaolo

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

LLMs for Generation of Architectural Components: An Exploratory Empirical Study in the Serverless World

Shrikara Arun, Meghana Tedla, Karthik Vaidhyanathan

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

Comments Accepted to IEEE International Conference on Software Architecture (ICSA) 2025 Main Track (https://conf.researchr.org/home/icsa-2025)

AI-Powered, But Power-Hungry? Energy Efficiency of LLM-Generated Code

Lola Solovyeva, Sophie Weidmann, Fernando Castor

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