代码大模型 / AI 编程

Geo-Code: A Code Framework for Reverse Code Generation from Geometric Images Based on Two-Stage Multi-Agent Evolution

Geo-Code: 一种基于双阶段多智能体演化的几何图像反向代码生成框架

Zhenyu Wu, Yanxi Long, Jian Li, Hua Huang

机构 * School of Artificial Intelligence, Beijing Normal University, Beijing, China（人工智能学院，北京师范大学，北京，中国） 纠错

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

AI总结 Geo-Code提出一种基于双阶段多智能体演化的几何图像反向代码生成框架，通过像素级锚定和度量驱动的代码演化提升几何重建精度和视觉一致性。

Comments ICML2026

Failure-Aware Enhancements for Large Language Model (LLM) Code Generation: An Empirical Study on Decision Framework

面向大语言模型（LLM）代码生成的失败意识增强：决策框架的实证研究

Jianru Shen, Zedong Peng, Lucy Owen

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

AI总结 本文通过实证研究，提出了一种基于失败特征的决策框架，用于指导大语言模型代码生成中的增强策略选择。

Comments Accepted at SANER 2026

Idea First, Code Later: Disentangling Problem Solving from Code Generation in Evaluating LLMs for Competitive Programming

先有想法，后写代码：在评估LLM用于竞技编程时，将问题解决与代码生成解耦

Sama Hadhoud, Alaa Elsetohy, Frederikus Hudi, Jan Christian Blaise Cruz, Steven Halim, Alham Fikri Aji

机构 * MBZUAI ； NAIST ； National University of Singapore（国立新加坡大学） 纠错

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

AI总结 本文提出通过编辑稿而非代码来评估LLM在竞技编程中的问题解决能力，并引入数据集和评估方法，强调区分问题解决与实现的重要性。

CODE ACROSTIC: Robust Watermarking for Code Generation

CODE ACROSTIC: 为代码生成提供稳健的水印技术

Li Lin, Siyuan Xin, Yang Cao, Xiaochun Cao

机构 * Institude of Science Tokyo（东京科学研究院） ； Shanghai University（上海大学） ； Sun Yat-sen University（孙中山大学） 纠错

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

AI总结 CODE ACROSTIC通过利用Cue List区分代码熵，提升代码水印标记的可检测性和实用性，有效应对注释移除攻击。

LEGO: A Layout Expression Language for Code Generation of Hierarchical Mapping

LEGO：一种用于分层映射代码生成的布局表达语言

Amir Mohammad Tavakkoli, Cosmin Oancea, Mary Hall

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

AI总结 LEGO是一种用于生成分层映射代码的布局表达语言，通过布局规范生成索引表达式，可集成至编译器和模板中，实现数据和计算优化。

Lost in Code Generation: Reimagining the Role of Software Models in AI-driven Software Engineering

Jürgen Cito, Dominik Bork

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

Comments Updated the bibliography to remove a few incorrect references and ensure all citations are accurate

Chemical classification program synthesis using generative artificial intelligence

Christopher J. Mungall, Adnan Malik, Daniel R. Korn, Justin T. Reese, Noel M. O'Boyle, Noel, Janna Hastings

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

Journal ref J Cheminform 17, 152 (2025)

Matricial Free Energy as a Gaussianizing Regularizer: Enhancing Autoencoders for Gaussian Code Generation

Rishi Sonthalia, Raj Rao Nadakuditi

机构 * Department of Mathematics, Boston College（数学系，波士顿学院） ； EECS, University of Michigan（电子工程与计算机科学系，密歇根大学） 纠错

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

LLM-VeriPPA: Power, Performance, and Area Optimization aware Verilog Code Generation with Large Language Models

Kiran Thorat, Jiahui Zhao, Yaotian Liu, Amit Hasan, Hongwu Peng, Xi Xie, Bin Lei, Caiwen Ding

机构 * Arizona State University（亚利桑那州立大学） 纠错

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

EvoCAD: Evolutionary CAD Code Generation with Vision Language Models

Tobias Preintner, Weixuan Yuan, Adrian König, Thomas Bäck, Elena Raponi, Niki van Stein

机构 * Institute of Advanced Computer Science, Leiden University, Leiden, The Netherlands（先进计算机科学研究所，莱顿大学，莱顿，荷兰） 纠错

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

Comments Accepted to IEEE ICTAI 2025

QUASAR: Quantum Assembly Code Generation Using Tool-Augmented LLMs via Agentic RL

Cong Yu, Valter Uotila, Shilong Deng, Qingyuan Wu, Tuo Shi, Songlin Jiang, Lei You, Bo Zhao

机构 * Aalto University（阿alto大学） ； University of Helsinki（赫尔辛基大学） ； University of Liverpool（利物浦大学） ； University of Southampton（南安普顿大学） ； Technical University of Denmark（丹麦技术大学） 纠错

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

A Preference-Driven Methodology for High-Quality Solidity Code Generation

Zhiyuan Peng, Xin Yin, Chenhao Ying, Chao Ni, Yuan Luo

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

VerilogMonkey: Exploring Parallel Scaling for Automated Verilog Code Generation with LLMs

Juxin Niu, Yuxin Du, Dan Niu, Xi Wang, Zhe Jiang, Nan Guan

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

Automating Code Generation for Semiconductor Equipment Control from Developer Utterances with LLMs

Youngkyoung Kim, Sanghyeok Park, Misoo Kim, Gangho Yoon, Eunseok Lee, Simon S. Woo

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

Conversational Code Generation: a Case Study of Designing a Dialogue System for Generating Driving Scenarios for Testing Autonomous Vehicles

Rimvydas Rubavicius, Antonio Valerio Miceli-Barone, Alex Lascarides, Subramanian Ramamoorthy

机构 * School of Informatics, University of Edinburgh 10 Crichton Street, Edinburgh EH8 9AB（信息学院，爱丁堡大学） 纠错

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

Comments In Proceedings of GeCoIn 2025: Generative Code Intelligence Workshop, co-located with ECAI-2025

AutoMisty: A Multi-Agent LLM Framework for Automated Code Generation in the Misty Social Robot

Xiao Wang, Lu Dong, Sahana Rangasrinivasan, Ifeoma Nwogu, Srirangaraj Setlur, Venugopal Govindaraju

机构 * State University of New York at Buffalo（纽约州立大学布法罗分校） ； Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham（计算机科学与工程系，阿米特拉学校 computing，阿米特拉世界大学） 纠错

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

Comments Accepted by IROS 2025

Embodied Long Horizon Manipulation with Closed-loop Code Generation and Incremental Few-shot Adaptation

Yuan Meng, Xiangtong Yao, Haihui Ye, Yirui Zhou, Shengqiang Zhang, Zhenguo Sun, Xukun Li, Zhenshan Bing, Alois Knoll

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

Comments update ICRA 6 page

ChronoLLM: Customizing Language Models for Physics-Based Simulation Code Generation

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

机构 * Department of Mechanical Engineering, University of Wisconsin-Madison（威斯康星大学麦迪逊分校机械工程系） ； Department of Computer Science, Rice University（里德大学计算机科学系） 纠错

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

Streamlined Airborne Software Development for Large UAVs: From Unified Data Collection to Automated Code Generation

Viktor Sinitsyn, Nils Schlautmann, Florian Schwaiger, Florian Holzapfel

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

ExploraCoder: Advancing code generation for multiple unseen APIs via planning and chained exploration

Yunkun Wang, Yue Zhang, Zhen Qin, Chen Zhi, Binhua Li, Fei Huang, Yongbin Li, Shuiguang Deng

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

How Are We Doing With Using AI-Based Programming Assistants For Privacy-Related Code Generation? The Developers' Experience

Kashumi Madampe, John Grundy, Nalin Arachchilage

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

Comments Accepted for publication at EASE'25 - short papers and emerging results track

CAD-Coder: An Open-Source Vision-Language Model for Computer-Aided Design Code Generation

Anna C. Doris, Md Ferdous Alam, Amin Heyrani Nobari, Faez Ahmed

机构 * Massachusetts Institute of Technology（麻省理工学院） 纠错

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

Are requirements really all you need? A case study of LLM-driven configuration code generation for automotive simulations

Krzysztof Lebioda, Nenad Petrovic, Fengjunjie Pan, Vahid Zolfaghari, Andre Schamschurko, Alois Knoll

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

CAD-Coder:Text-Guided CAD Files Code Generation

Changqi He, Shuhan Zhang, Liguo Zhang, Jiajun Miao

机构 * College of Computer Science and Technology, Harbin Engineering University（计算机科学与技术学院，哈尔滨工程大学） 纠错

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

The Hidden Risks of LLM-Generated Web Application Code: A Security-Centric Evaluation of Code Generation Capabilities in Large Language Models

Swaroop Dora, Deven Lunkad, Naziya Aslam, S. Venkatesan, Sandeep Kumar Shukla

机构 * Department of IT IIIT Allahabad（信息技术系，印度阿拉哈巴德IIIT） ； Department of ECE IIIT Allahabad（电子工程系，印度阿拉哈巴德IIIT） ； Department of CSE IIT Kanpur（计算机科学与工程系，印度坎purIIT） 纠错

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

Comments 9 pages

Evaluating Code Generation of LLMs in Advanced Computer Science Problems

Emir Catir, Robin Claesson, Rodothea Myrsini Tsoupidi

机构 * Royal Institute of Technology（皇家理工学院） 纠错

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

Quality In, Quality Out: Investigating Training Data's Role in AI Code Generation

Cristina Improta, Rosalia Tufano, Pietro Liguori, Domenico Cotroneo, Gabriele Bavota

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

Comments Accepted to the 33rd IEEE/ACM International Conference on Program Comprehension (ICPC 2025)

SolSearch: An LLM-Driven Framework for Efficient SAT-Solving Code Generation

Junjie Sheng, Yanqiu Lin, Jiehao Wu, Yanhong Huang, Jianqi Shi, Min Zhang, Xiangfeng Wang

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

ScriptoriumWS: A Code Generation Assistant for Weak Supervision

Tzu-Heng Huang, Catherine Cao, Spencer Schoenberg, Harit Vishwakarma, Nicholas Roberts, Frederic Sala

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

Comments Appeared in ICLR'23 Deep Learning for Code (DL4C) Workshop & 2023 Midwest Machine Learning Symposium

Benchmarking Language Model Creativity: A Case Study on Code Generation

Yining Lu, Dixuan Wang, Tianjian Li, Dongwei Jiang, Sanjeev Khudanpur, Meng Jiang, Daniel Khashabi

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