代码大模型 / AI 编程

Wisdom and Delusion of LLM Ensembles for Code Generation and Repair

Fernando Vallecillos-Ruiz, Max Hort, Leon Moonen

机构 * Simula Research Laboratory（Simula研究实验室） 纠错

专题命中 代码生成 ：code generation(title,abstract)；program repair(abstract)；分类 cs.SE、cs.CL、cs.LG

Comments Added Acknowledgments section and hyphenated last names

Self-Evolving Curriculum for LLM Reasoning

Xiaoyin Chen, Jiarui Lu, Minsu Kim, Dinghuai Zhang, Jian Tang, Alexandre Piché, Nicolas Gontier, Yoshua Bengio, Ehsan Kamalloo

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

Beyond Length: Quantifying Long-Range Information for Long-Context LLM Pretraining Data

Haoran Deng, Yingyu Lin, Zhenghao Lin, Xiao Liu, Yizhou Sun, Yi-An Ma, Yeyun Gong

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

Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections

David Schmotz, Sahar Abdelnabi, Maksym Andriushchenko

机构 * ELLIS Institute Tübingen（图宾根ELLIS研究所） ； MPI for Intelligent Systems Tübingen（图宾根智能系统研究所） ； AI Center（人工智能中心） 纠错

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

Nexus: Execution-Grounded Multi-Agent Test Oracle Synthesis

Dong Huang, Mingzhe Du, Jie M. Zhang, Zheng Lin, Meng Luo, Qianru Zhang, See-Kiong Ng

机构 * NUS（新加坡国立大学） 纠错

专题命中 代码评测 ：program repair(abstract)；分类 cs.SE、cs.CL

Comments Under Review

Lean4Physics: Comprehensive Reasoning Framework for College-level Physics in Lean4

Yuxin Li, Minghao Liu, Ruida Wang, Wenzhao Ji, Zhitao He, Rui Pan, Junming Huang, Tong Zhang, Yi R. Fung

机构 * Hong Kong University of Science and Technology（香港科技大学） ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； Princeton University（普林斯顿大学） 纠错

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

Massive Supervised Fine-tuning Experiments Reveal How Data, Layer, and Training Factors Shape LLM Alignment Quality

Yuto Harada, Yusuke Yamauchi, Yusuke Oda, Yohei Oseki, Yusuke Miyao, Yu Takagi

机构 * NII LLMC（日本信息处理学会大语言模型中心） ； The University of Tokyo（东京大学） ； NAIST（日本科学技术大学） ； Nagoya Institute of Technology（名古屋技术大学） 纠错

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

Comments Accepted to EMNLP 2025 (Main Conference). Models and evaluation results available at: https://github.com/llm-jp/massive-sft

Empowering RepoQA-Agent based on Reinforcement Learning Driven by Monte-carlo Tree Search

Guochang Li, Yuchen Liu, Zhen Qin, Yunkun Wang, Jianping Zhong, Chen Zhi, Binhua Li, Fei Huang, Yongbin Li, Shuiguang Deng

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

Establishing Baselines for Photonic Quantum Machine Learning: Insights from an Open, Collaborative Initiative

Cassandre Notton, Vassilis Apostolou, Agathe Senellart, Anthony Walsh, Daphne Wang, Yichen Xie, Songqinghao Yang, Ilyass Mejdoub, Oussama Zouhry, Kuan-Cheng Chen, Chen-Yu Liu, Ankit Sharma, Edara Yaswanth Balaji, Soham Prithviraj Pawar, Ludovic Le Frioux, Valentin Macheret, Antoine Radet, Valentin Deumier, Ashesh Kumar Gupta, Gabriele Intoccia, Dimitri Jordan Kenne, Chiara Marullo, Giovanni Massafra, Nicolas Reinaldet, Vincenzo Schiano Di Cola, Danylo Kolesnyk, Yelyzaveta Vodovozova, Rawad Mezher, Pierre-Emmanuel Emeriau, Alexia Salavrakos, Jean Senellart

专题命中 代码评测 ：repository(abstract)

Brightify: A tool for calculating directionally-resolved brightness in neutron sources

Mina Akhyani, Luca Zanini, Henrik Rønnow

专题命中 代码评测 ：repository(abstract)

Journal ref Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment Volume 1082, Part 2, February 2026, 171037

Gistify! Codebase-Level Understanding via Runtime Execution

Hyunji Lee, Minseon Kim, Chinmay Singh, Matheus Pereira, Atharv Sonwane, Isadora White, Elias Stengel-Eskin, Mohit Bansal, Zhengyan Shi, Alessandro Sordoni, Marc-Alexandre Côté, Xingdi Yuan, Lucas Caccia

机构 * University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校） ； Microsoft Research（微软研究院） ； Cornell University（康奈尔大学） ； University of California San Diego（加州大学圣地亚哥分校） ； University of Texas at Austin（德克萨斯大学奥斯汀分校） 纠错

专题命中 仓库级理解 ：coding agent(abstract)；分类 cs.CL、cs.AI

Hybrid DQN-TD3 Reinforcement Learning for Autonomous Navigation in Dynamic Environments

Xiaoyi He, Danggui Chen, Zhenshuo Zhang, Zimeng Bai

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

Comments 6 pages, 5 figures; ROS+Gazebo (TurtleBot3) implementation; evaluation with PathBench metrics; code (primary): https://github.com/MayaCHEN-github/HierarchicalRL-robot-navigation; mirror (for reproducibility): https://github.com/ShowyHe/DRL-robot-navigation

Curly Flow Matching for Learning Non-gradient Field Dynamics

Katarina Petrović, Lazar Atanackovic, Viggo Moro, Kacper Kapuśniak, İsmail İlkan Ceylan, Michael Bronstein, Avishek Joey Bose, Alexander Tong

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

Comments Accepted to NeurIPS 2025

Scalpel: Automotive Deep Learning Framework Testing via Assembling Model Components

Yinglong Zou, Juan Zhai, Chunrong Fang, An Guo, Jiawei Liu, Zhenyu Chen

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

Comments Accepted by the 48th IEEE/ACM International Conference on Software Engineering (ICSE 2026)

Assignment-Routing Optimization : Efficient Heuristic Solver with Shaking Algorithm

Yuan Qilong, Michal Pavelka

专题命中 仓库级理解 ：repository(abstract)

Comments 16 pages, 5 figures

Evaluating Argon2 Adoption and Effectiveness in Real-World Software

Pascal Tippe, Michael P. Berner

专题命中 仓库级理解 ：repository(abstract)

Comments This preprint has not undergone peer review or any post-submission improvements or corrections. The Version of Record of this contribution is published in Volume 15993 of the Lecture Notes in Computer Science series, and is available online at https://doi.org/10.1007/978-3-032-00627-1_2