AI 大模型

代码大模型 / AI 编程

代码生成、软件工程智能体、程序修复、测试生成和开发者工具。

2025-10-22 至 2025-10-22 共收录 6 篇信号源：cs.SE, cs.CL, cs.AI, cs.LG, cs.PL

1. 仓库级理解 6 篇

2510.10806 2025-10-22 cs.CL cs.AI cs.IR cs.LG 67%

Is Implicit Knowledge Enough for LLMs? A RAG Approach for Tree-based Structures

Mihir Gupte, Paolo Giusto, Ramesh S

机构 * General Motors（通用汽车公司）

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

Comments Waiting for Conference Response

2510.18475 2025-10-22 cs.CL 57%

DART: A Structured Dataset of Regulatory Drug Documents in Italian for Clinical NLP

Mariano Barone, Antonio Laudante, Giuseppe Riccio, Antonio Romano, Marco Postiglione, Vincenzo Moscato

机构 * University of Naples Federico II, Department of Electrical Engineering（那不勒斯费德里科二世大学电气工程系）； Consorzio Interuniversitario Nazionale per l'Informatica (CINI) - ITEM National Lab, Complesso Universitario Monte S.Angelo, Naples, Italy（国家信息计算联合研究所（CINI）- ITEM国家实验室，那不勒斯意大利大学综合体）； Northwestern University, Department of Computer Science, McCormick School of Engineering（西北大学计算机科学系，麦科姆工程学院）

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

Journal ref ITADATA 2025: 4th Italian Conference on Big Data and Data Science, Turin, Italy, September 9-11, 2025

2510.17142 2025-10-22 cs.SE 57%

PEACE: Towards Efficient Project-Level Efficiency Optimization via Hybrid Code Editing

Xiaoxue Ren, Jun Wan, Yun Peng, Zhongxin Liu, Ming Liang, Dajun Chen, Wei Jiang, Yong Li

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

Journal ref ASE 2025

2503.23804 2025-10-22 cs.CR cs.CL cs.IR cs.MA 57%

DrunkAgent: Stealthy Memory Corruption in LLM-Powered Recommender Agents

Shiyi Yang, Zhibo Hu, Xinshu Li, Chen Wang, Tong Yu, Xiwei Xu, Liming Zhu, Lina Yao

机构 * The University of New South Wales（新南威尔士大学）； Macquarie University（麦考瑞大学）； Adobe Research（Adobe研究）

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

2510.18033 2025-10-22 cond-mat.mtrl-sci 50%

Benchmarking 34 OpenKIM Nickel Potentials with an Emphasis on Surfaces and Extended Defects

Matthew Thoms, Hao Sun, Laurent Karim Béland

专题命中仓库级理解：repository(abstract)

Comments 38 pages, 10 figures, to be submitted to computational materials science, code available at https://gitlab.com/mattmtl/ni-pots-tests

2509.01536 2025-10-22 cs.IR 50%

AI4DiTraRe: Building the BFO-Compliant Chemotion Knowledge Graph

Ebrahim Norouzi, Nicole Jung, Anna M. Jacyszyn, Jörg Waitelonis, Harald Sack

专题命中仓库级理解：repository(abstract)

Comments 12 pages, 7 figures. Camera-ready version. Accepted to the 5th International Workshop on Scientific Knowledge: Representation, Discovery, and Assessment; 2 November 2025 - Nara, Japan; co-located with The 24th International Semantic Web Conference, ISWC 2025. Published in CEUR proceedings Vol-4065, pages 45-56