代码大模型 / AI 编程

From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation

Ke Niu, Haiyang Yu, Zhuofan Chen, Mengyang Zhao, Teng Fu, Bin Li, Xiangyang Xue

机构 * Fudan University（复旦大学） ； ByteDance Inc（字节跳动公司） 纠错

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

MHPP: Exploring the Capabilities and Limitations of Language Models Beyond Basic Code Generation

Jianbo Dai, Jianqiao Lu, Yunlong Feng, Guangtao Zeng, Rongju Ruan, Ming Cheng, Dong Huang, Haochen Tan, Zhijiang Guo

机构 * University of Edinburgh（爱丁堡大学） ； The University of Hong Kong（香港大学） ； Harbin Institute of Technology（哈尔滨工业大学） ； Singapore University of Technology and Design（新加坡科技设计大学） ； South China University of Technology（华南理工大学） ； City University of Hong Kong（香港城市大学） ； University of Cambridge（剑桥大学） 纠错

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

Comments 43 pages, dataset and code are available at https://github.com/SparksofAGI/MHPP, leaderboard can be found at https://sparksofagi.github.io/MHPP/

Reinforcement Learning with Rubric Anchors

Zenan Huang, Yihong Zhuang, Guoshan Lu, Zeyu Qin, Haokai Xu, Tianyu Zhao, Ru Peng, Jiaqi Hu, Zhanming Shen, Xiaomeng Hu, Xijun Gu, Peiyi Tu, Jiaxin Liu, Wenyu Chen, Yuzhuo Fu, Zhiting Fan, Yanmei Gu, Yuanyuan Wang, Zhengkai Yang, Jianguo Li, Junbo Zhao

机构 * Inclusion AI ； Ant Group（蚂蚁集团） ； Zhejiang University（浙江大学） 纠错

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

Comments technical report

Uncovering Systematic Failures of LLMs in Verifying Code Against Natural Language Specifications

Haolin Jin, Huaming Chen

机构 * University of Sydney（悉尼大学） 纠错

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

Comments Accepted to the NIER track of the 40th IEEE/ACM International Conference on Automated Software Engineering (ASE 2025)

Rethinking Autonomy: Preventing Failures in AI-Driven Software Engineering

Satyam Kumar Navneet, Joydeep Chandra

机构 * Department of CSE Chandigarh University Mohali, India（计算机科学与工程系 奇纳格里大学 莫哈利，印度） ； Department of CST Tsinghua University Beijing, China（计算机科学与技术系 清华大学 北京，中国） 纠错

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

System-driven Interactive Design Support for Cloud Architecture: A Qualitative User Experience Study with Novice Engineers

Ryosuke Kohita, Akira Kasuga

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

Optimizing Language Models for Inference Time Objectives using Reinforcement Learning

Yunhao Tang, Kunhao Zheng, Gabriel Synnaeve, Rémi Munos

机构 * Meta GenAI（Meta 生成式人工智能） ； Meta FAIR 纠错

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

Comments Published as a conference paper at ICML 2025

Chart-CoCa: Self-Improving Chart Understanding of Vision LMs via Code-Driven Synthesis and Candidate-Conditioned Answering

Gongyao Jiang, Qiong Luo

机构 * The Hong Kong University of Science 纠错

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

Comments Accepted to CIKM 2025

Consiglieres in the Shadow: Understanding the Use of Uncensored Large Language Models in Cybercrimes

Zilong Lin, Zichuan Li, Xiaojing Liao, XiaoFeng Wang

专题命中 代码生成 ：code generation(abstract)

Synthesiz3 This: an SMT-Based Approach for Synthesis with Uncomputable Symbols

Petra Hozzová, Nikolaj Bjørner

专题命中 代码生成 ：program synthesis(abstract)

Comments This is the version of this paper accepted for FMCAD 2025

Illuminating LLM Coding Agents: Visual Analytics for Deeper Understanding and Enhancement

Junpeng Wang, Yuzhong Chen, Menghai Pan, Chin-Chia Michael Yeh, Mahashweta Das

机构 * Visa Research（Visa研究） 纠错

专题命中 软件智能体 ：coding agent(title,abstract)；code generation(abstract)；分类 cs.LG

Comments 11 pages, 10 figures

Help or Hurdle? Rethinking Model Context Protocol-Augmented Large Language Models

Wei Song, Haonan Zhong, Ziqi Ding, Jingling Xue, Yuekang Li

专题命中 代码评测 ：code generation(abstract)；分类 cs.AI

Game Reasoning Arena: A Framework and Benchmark for Assessing Reasoning Capabilities of Large Language Models via Game Play

Lucia Cipolina-Kun, Marianna Nezhurina, Jenia Jitsev

机构 * LAION Juelich Supercomputing Center (JSC)（LAION尤利奇超级计算机中心（JSC）） ； Research Center Juelich (FZJ)（尤利奇研究中心（FZJ）） 纠错

专题命中 代码评测 ：repository(abstract)；分类 cs.AI

S2FGL: Spatial Spectral Federated Graph Learning

Zihan Tan, Suyuan Huang, Guancheng Wan, Wenke Huang, He Li, Mang Ye

机构 * National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China（多媒体软件国家工程研究中心，计算机科学学院，武汉大学，武汉，中国） 纠错

专题命中 仓库级理解 ：repository(abstract)；分类 cs.AI、cs.LG

GeoSAM: Fine-tuning SAM with Multi-Modal Prompts for Mobility Infrastructure Segmentation

Rafi Ibn Sultan, Chengyin Li, Hui Zhu, Prashant Khanduri, Marco Brocanelli, Dongxiao Zhu

机构 * Department of Computer Science, Wayne State University, Detroit, MI, USA 48202（计算机科学系，韦恩州立大学） ； Department of Radiation Oncology, Henry Ford Health, Detroit, MI, USA 48202（放射肿瘤科，亨利福特健康） ； Department of Electrical and Computer Engineering, The Ohio State University, Columbus, Ohio, USA 43210（电气与计算机工程系，俄亥俄州立大学） 纠错

专题命中 仓库级理解 ：repository(abstract)；分类 cs.AI

Comments Accepted by European Conference on Artificial Intelligence (ECAI 2025)