代码大模型 / AI 编程

GameGPT: Multi-agent Collaborative Framework for Game Development

Dake Chen, Haoyang Zhang, Hanbin Wang, Yunhao Huo, Yuzhao Li, Junjie Wang

机构 * AutoGame Research（AutoGame研究所） ； X-Institute（X研究所） ； University of Southern California（南加州大学） ； Tsinghua University（清华大学） 纠错

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

Synthesizing Optimal Object Selection Predicates for Image Editing using Lattices

Yang He, Xiaoyu Liu, Yuepeng Wang

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

Comments We identified issues in the experimental results and want to withdraw the paper. We plan to submit an updated version once these issues have been resolved

CoreThink: A Symbolic Reasoning Layer to reason over Long Horizon Tasks with LLMs

Jay Vaghasiya, Omkar Ghugarkar, Vishvesh Bhat, Vipul Dholaria, Julian McAuley

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

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement

Yueke Zhang, Yifan Zhang, Kevin Leach, Yu Huang

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

Comments 6 Pages

Evaluating Efficiency and Novelty of LLM-Generated Code for Graph Analysis

Atieh Barati Nia, Mohammad Dindoost, David A. Bader

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

Comments 7 pages, v2: minor revision to match final paper published in the The 29th Annual IEEE High Performance Extreme Computing Conference (HPEC), Virtual, September 15-19, 2025. Outstanding Student Paper Award

Re-evaluating LLM-based Heuristic Search: A Case Study on the 3D Packing Problem

Guorui Quan, Mingfei Sun, Manuel López-Ibáñez

机构 * The University of Manchester（曼彻斯特大学） ； University of Manchester（曼彻斯特大学） ； Department of Computer Science（计算机科学系） ； Alliance Manchester Business School（曼彻斯特商业联盟学院） 纠错

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

RewardDS: Privacy-Preserving Fine-Tuning for Large Language Models via Reward Driven Data Synthesis

Jianwei Wang, Chengming Shi, Junyao Yang, Haoran Li, Qianli Ma, Huiping Zhuang, Cen Chen, Ziqian Zeng

机构 * South China University of Technology（华南理工大学） 纠错

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

Comments Accepted by EMNLP2025 Main

Detecting Stealthy Data Poisoning Attacks in AI Code Generators

Cristina Improta

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

Comments Accepted to the 3rd IEEE International Workshop on Reliable and Secure AI for Software Engineering (ReSAISE, 2025), co-located with ISSRE 2025

SimuGen: Multi-modal Agentic Framework for Constructing Block Diagram-Based Simulation Models

Xinxing Ren, Qianbo Zang, Zekun Guo

机构 * Brunel University of London（伦敦布鲁内尔大学） ； SnT, Université du Luxembourg（卢森堡大学SnT分校） ； University of Hull（霍尔姆斯大学） 纠错

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

MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement

Jaehyun Nam, Jinsung Yoon, Jiefeng Chen, Jinwoo Shin, Sercan Ö. Arık, Tomas Pfister

机构 * Google Cloud（谷歌云） ； KAIST（韩国科学技术院） 纠错

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

Doc2Chart: Intent-Driven Zero-Shot Chart Generation from Documents

Akriti Jain, Pritika Ramu, Aparna Garimella, Apoorv Saxena

机构 * Adobe Research（Adobe研究院） 纠错

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

Comments Accepted to EMNLP 2025 Main Conference

Structured Agentic Workflows for Financial Time-Series Modeling with LLMs and Reflective Feedback

Yihao Ang, Yifan Bao, Lei Jiang, Jiajie Tao, Anthony K. H. Tung, Lukasz Szpruch, Hao Ni

机构 * National University of Singapore（新加坡国立大学） ； University College London（伦敦大学学院） ； University of Edinburgh（爱丁堡大学） 纠错

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

MALMM: Multi-Agent Large Language Models for Zero-Shot Robotics Manipulation

Harsh Singh, Rocktim Jyoti Das, Mingfei Han, Preslav Nakov, Ivan Laptev

机构 * Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学） 纠错

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

Comments 48 pages

Using LLMs and Essence to Support Software Practice Adoption

Sonia Nicoletti, Paolo Ciancarini

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

Gradual Metaprogramming

Tianyu Chen, Darshal Shetty, Jeremy G. Siek, Chao-Hong Chen, Weixi Ma, Arnaud Venet, Rocky Liu

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

Comments 14 pages, 10 figures

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

Towards Efficient Hash Maps in Functional Array Languages

William Henrich Due, Martin Elsman, Troels Henriksen

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

CPO: Addressing Reward Ambiguity in Role-playing Dialogue via Comparative Policy Optimization

Xinge Ye, Rui Wang, Yuchuan Wu, Victor Ma, Feiteng Fang, Fei Huang, Yongbin Li

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

AdaptFlow: Adaptive Workflow Optimization via Meta-Learning

Runchuan Zhu, Bowen Jiang, Lingrui Mei, Fangkai Yang, Lu Wang, Haoxiang Gao, Fengshuo Bai, Pu Zhao, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang

机构 * Peking University（北京大学） ； University of Chinese Academy of Sciences（中国科学院大学） ； Microsoft（微软公司） ； Shanghai Jiaotong University（上海交通大学） 纠错

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

A Taxonomy of Inefficiencies in LLM-Generated Python Code

Altaf Allah Abbassi, Leuson Da Silva, Amin Nikanjam, Foutse Khomh

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

Optimizing Prompt Sequences using Monte Carlo Tree Search for LLM-Based Optimization

Fei Xu Yu, Gina Adam, Nathaniel D. Bastian, Tian Lan

机构 * The George Washington University（乔治·华盛顿大学） ； United States Military Academy（美国军事学院） 纠错

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

KG-Augmented Executable CoT for Mathematical Coding

Xingyu Chen, Junxiu An, Jun Guo, Li Wang, Jingcai Guo

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

Comments 9 pages,2figures,6 tables

Analyzing Prominent LLMs: An Empirical Study of Performance and Complexity in Solving LeetCode Problems

Everton Guimaraes, Nathalia Nascimento, Chandan Shivalingaiah, Asish Nelapati

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

Comments 11 pages, 13 figures, 29th International Conference on Evaluation and Assessment in Software Engineering (EASE)

A Human Centric Requirements Engineering Framework for Assessing Github Copilot Output

Soroush Heydari

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

Comments 8 pages

RTLCoder: Outperforming GPT-3.5 in Design RTL Generation with Our Open-Source Dataset and Lightweight Solution

Shang Liu, Wenji Fang, Yao Lu, Qijun Zhang, Hongce Zhang, Zhiyao Xie

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

Comments This is the LAD Conference version of RTLCoder, for the TCAD extension version, please refer to: arXiv:2312.08617v4

SmartLLMs Scheduler: A Framework for Cost-Effective LLMs Utilization

Yueyue Liu, Hongyu Zhang, Yuantian Miao

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

Everyone Contributes! Incentivizing Strategic Cooperation in Multi-LLM Systems via Sequential Public Goods Games

Yunhao Liang, Yuan Qu, Jingyuan Yang, Shaochong Lin, Zuo-Jun Max Shen

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

Testing the Untestable? An Empirical Study on the Testing Process of LLM-Powered Software Systems

Cleyton Magalhaes, Italo Santos, Brody Stuart-Verner, Ronnie de Souza Santos

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