代码大模型 / AI 编程 - arXivDaily 专题

2511.04132 2025-11-07 cs.LG 57%

Exploring the Feasibility of End-to-End Large Language Model as a Compiler

Hongbin Zhang, Shihao Gao, Yang Liu, Mingjie Xing, Yanjun Wu, Chen Zhao

机构 * Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）； University of Chinese Academy of Sciences（中国科学院大学）

专题命中程序分析与验证：code generation(abstract)；分类 cs.LG

Comments This work has been accepted by IJCNN 2025 and submitted to the IEEE for publication

2510.11151 2025-10-14 cs.CL cs.CR 57%

TypePilot: Leveraging the Scala Type System for Secure LLM-generated Code

Alexander Sternfeld, Andrei Kucharavy, Ljiljana Dolamic

机构 * Institute of Entrepreneurship & Management, HES-SO Le Foyer, Techno-Pôle 1 Sierre, Switzerland（创业与管理学院，HES-SO莱福院，技术园区1，瑞士）； Institute of Informatics, HES-SO Techno-Pôle 3 Sierre, Switzerland（信息学院，HES-SO技术园区3，瑞士）； Cyber-Defence Campus armasuisse, Science and Technology Thun, Switzerland（网络安全校区，armasuisse，科技，瑞士）

专题命中程序分析与验证：code generation(abstract)；分类 cs.CL

2510.09932 2025-10-14 cs.PL cs.AR 57%

ACT: Automatically Generating Compiler Backends from Tensor Accelerator ISA Descriptions

Devansh Jain, Akash Pardeshi, Marco Frigo, Krut Patel, Kaustubh Khulbe, Jai Arora, Charith Mendis

专题命中程序分析与验证：code generation(abstract)；分类 cs.PL

2504.06421 2025-10-07 cs.PL 57%

We've Got You Covered: Type-Guided Repair of Incomplete Input Generators

Patrick LaFontaine, Zhe Zhou, Ashish Mishra, Suresh Jagannathan, Benjamin Delaware

专题命中程序分析与验证：program repair(abstract)；分类 cs.PL

Comments Extended version of OOPSLA 2025 paper

2509.14589 2025-09-19 cs.CR cs.AI 57%

ATLANTIS: AI-driven Threat Localization, Analysis, and Triage Intelligence System

Taesoo Kim, HyungSeok Han, Soyeon Park, Dae R. Jeong, Dohyeok Kim, Dongkwan Kim, Eunsoo Kim, Jiho Kim, Joshua Wang, Kangsu Kim, Sangwoo Ji, Woosun Song, Hanqing Zhao, Andrew Chin, Gyejin Lee, Kevin Stevens, Mansour Alharthi, Yizhuo Zhai, Cen Zhang, Joonun Jang, Yeongjin Jang, Ammar Askar, Dongju Kim, Fabian Fleischer, Jeongin Cho, Junsik Kim, Kyungjoon Ko, Insu Yun, Sangdon Park, Dowoo Baik, Haein Lee, Hyeon Heo, Minjae Gwon, Minjae Lee, Minwoo Baek, Seunggi Min, Wonyoung Kim, Yonghwi Jin, Younggi Park, Yunjae Choi, Jinho Jung, Gwanhyun Lee, Junyoung Jang, Kyuheon Kim, Yeonghyeon Cha, Youngjoon Kim

专题命中程序分析与验证：program repair(abstract)；分类 cs.AI

Comments Version 1.0 (September 17, 2025). Technical Report. Team Atlanta -- 1st place in DARPA AIxCC Final Competition. Project page: https://team-atlanta.github.io/

2508.14419 2025-08-21 cs.SE 57%

Static Analysis as a Feedback Loop: Enhancing LLM-Generated Code Beyond Correctness

Scott Blyth, Sherlock A. Licorish, Christoph Treude, Markus Wagner

专题命中程序分析与验证：code generation(abstract)；分类 cs.SE

2506.02233 2025-06-04 cs.PL 57%

Improving compiler support for SIMD offload using Arm Streaming SVE

Mohamed Husain Noor Mohamed, Adarsh Patil, Latchesar Ionkov, Eric Van Hensbergen

专题命中程序分析与验证：code generation(abstract)；分类 cs.PL

2505.22610 2025-05-29 cs.PL 57%

TPDE: A Fast Adaptable Compiler Back-End Framework

Tobias Schwarz, Tobias Kamm, Alexis Engelke

专题命中程序分析与验证：code generation(abstract)；分类 cs.PL

Comments 23 pages, 10 figures

2505.09363 2025-05-16 cs.PL 57%

eqsat: An Equality Saturation Dialect for Non-destructive Rewriting

Jules Merckx, Alexandre Lopoukhine, Samuel Coward, Jianyi Cheng, Bjorn De Sutter, Tobias Grosser

专题命中程序分析与验证：program synthesis(abstract)；分类 cs.PL

Comments Accepted as workshop paper at the EGRAPHS 2025 workshop

2503.19174 2025-05-16 cs.AI 57%

AssertionForge: Enhancing Formal Verification Assertion Generation with Structured Representation of Specifications and RTL

Yunsheng Bai, Ghaith Bany Hamad, Syed Suhaib, Haoxing Ren

机构 * NVIDIA（英伟达）

专题命中程序分析与验证：code generation(abstract)；分类 cs.AI

Comments LAD 2025

2504.09118 2025-04-15 cs.CL 57%

Optimizing FDTD Solvers for Electromagnetics: A Compiler-Guided Approach with High-Level Tensor Abstractions

Yifei He, Måns I. Andersson, Stefano Markidis

专题命中程序分析与验证：code generation(abstract)；分类 cs.CL

2502.04063 2025-02-07 cs.PL 57%

A Multi-level Compiler Backend for Accelerated Micro-kernels Targeting RISC-V ISA Extensions

Alexandre Lopoukhine, Federico Ficarelli, Christos Vasiladiotis, Anton Lydike, Josse Van Delm, Alban Dutilleul, Luca Benini, Marian Verhelst, Tobias Grosser

专题命中程序分析与验证：code generation(abstract)；分类 cs.PL

2501.09201 2025-01-17 cs.PL cs.SC 57%

Towards Semantics Lifting for Scientific Computing: A Case Study on FFT

Naifeng Zhang, Sanil Rao, Mike Franusich, Franz Franchetti

专题命中程序分析与验证：code generation(abstract)；分类 cs.PL

Comments Accepted at the Theory and Practice of Static Analysis Workshop (TPSA), in conjunction with the ACM SIGPLAN Symposium on Principles of Programming Languages (POPL), 2025

2403.19072 2024-11-21 cs.CR cs.SE 57%

AssetHarvester: A Static Analysis Tool for Detecting Secret-Asset Pairs in Software Artifacts

Setu Kumar Basak, K. Virgil English, Ken Ogura, Vitesh Kambara, Bradley Reaves, Laurie Williams

专题命中程序分析与验证：repository(abstract)；分类 cs.SE

Comments Accepted in the proceedings of the 47th International Conference on Software Engineering (ICSE 2025)

2411.09391 2024-11-15 cs.PL 57%

An Optimizing Just-In-Time Compiler for Rotor

João H. Trindade, José C. Silva

专题命中程序分析与验证：code generation(abstract)；分类 cs.PL

Comments First International Conference of Innovative Views of .NET Technologies, June 2005

Journal ref TProceedings of the First International Conference of Innovative Views of .NET Technologies, 107-121. Porto, Portugal. ISBN 972-8688-31-8 (2005)

2410.23299 2024-11-01 cs.AR cs.AI 57%

FVEval: Understanding Language Model Capabilities in Formal Verification of Digital Hardware

Minwoo Kang, Mingjie Liu, Ghaith Bany Hamad, Syed Suhaib, Haoxing Ren

专题命中程序分析与验证：code generation(abstract)；分类 cs.AI

2410.13007 2024-10-18 cs.SE 57%

Codellm-Devkit: A Framework for Contextualizing Code LLMs with Program Analysis Insights

Rahul Krishna, Rangeet Pan, Raju Pavuluri, Srikanth Tamilselvam, Maja Vukovic, Saurabh Sinha

专题命中程序分析与验证：code generation(abstract)；分类 cs.SE

2409.13768 2024-09-24 cs.CR cs.AI 57%

Magika: AI-Powered Content-Type Detection

Yanick Fratantonio, Luca Invernizzi, Loua Farah, Kurt Thomas, Marina Zhang, Ange Albertini, Francois Galilee, Giancarlo Metitieri, Julien Cretin, Alex Petit-Bianco, David Tao, Elie Bursztein

专题命中程序分析与验证：repository(abstract)；分类 cs.AI

2203.11115 2024-09-12 cs.SE 57%

To Type or Not to Type? A Systematic Comparison of the Software Quality of JavaScript and TypeScript Applications on GitHub

Justus Bogner, Manuel Merkel

专题命中程序分析与验证：repository(abstract)；分类 cs.SE

Comments Accepted at MSR '22 (19th International Conference on Mining Software Repositories)

2407.02095 2024-08-14 cs.SE 57%

TIGER: A Generating-Then-Ranking Framework for Practical Python Type Inference

Chong Wang, Jian Zhang, Yiling Lou, Mingwei Liu, Weisong Sun, Yang Liu, Xin Peng

专题命中程序分析与验证：code model(abstract)；分类 cs.SE

Comments Accepted by ICSE'25

2307.00593 2024-05-09 cs.SE 57%

Isolating Compiler Bugs by Generating Effective Witness Programs with Large Language Models

Haoxin Tu, Zhide Zhou, He Jiang, Imam Nur Bani Yusuf, Yuxian Li, Lingxiao Jiang

专题命中程序分析与验证：code generation(abstract)；分类 cs.SE

Comments Accepted by IEEE Transactions on Software Engineering

2403.12627 2024-04-03 cs.AI cs.LO 57%

Enhancing Formal Theorem Proving: A Comprehensive Dataset for Training AI Models on Coq Code

Andreas Florath

专题命中程序分析与验证：code generation(abstract)；分类 cs.AI

Comments 11 pages

2301.01333 2024-03-12 cs.LG cs.PF 57%

oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation

Jianhui Li, Zhennan Qin, Yijie Mei, Jingze Cui, Yunfei Song, Ciyong Chen, Yifei Zhang, Longsheng Du, Xianhang Cheng, Baihui Jin, Yan Zhang, Jason Ye, Eric Lin, Dan Lavery

专题命中程序分析与验证：code generation(abstract)；分类 cs.LG

Comments 10 pages excluding reference, 9 figures, 1 table

2310.04963 2024-03-12 cs.AI 57%

LLM4VV: Developing LLM-Driven Testsuite for Compiler Validation

Christian Munley, Aaron Jarmusch, Sunita Chandrasekaran

专题命中程序分析与验证：code generation(abstract)；分类 cs.AI

2401.06619 2024-01-15 cs.SE 57%

PyTy: Repairing Static Type Errors in Python

Yiu Wai Chow, Luca Di Grazia, Michael Pradel

专题命中程序分析与验证：program repair(abstract)；分类 cs.SE

Journal ref ICSE 2024

2311.14443 2023-11-27 cs.PL 57%

Petit programming language and compiler

Raul Barbosa

专题命中程序分析与验证：code generation(abstract)；分类 cs.PL

2311.06505 2023-11-14 cs.LG 57%

CompCodeVet: A Compiler-guided Validation and Enhancement Approach for Code Dataset

Le Chen, Arijit Bhattacharjee, Nesreen K. Ahmed, Niranjan Hasabnis, Gal Oren, Bin Lei, Ali Jannesari

专题命中程序分析与验证：code generation(abstract)；分类 cs.LG

2309.08118 2023-09-18 cs.PL 57%

Graph IRs for Impure Higher-Order Languages (Technical Report)

Oliver Bračevac, Guannan Wei, Songlin Jia, Supun Abeysinghe, Yuxuan Jiang, Yuyan Bao, Tiark Rompf

专题命中程序分析与验证：code generation(abstract)；分类 cs.PL

Comments arXiv admin note: text overlap with arXiv:2309.05885

2309.05483 2023-09-12 cs.PL 57%

Sound Atomicity Inference for Data-Centric Synchronization

Hervé Paulino, Ana Almeida Matos, Jan Cederquist, Marco Giunti, João Matos, António Ravara

专题命中程序分析与验证：code generation(abstract)；分类 cs.PL

2309.02467 2023-09-07 cs.LG cs.CY 57%

Developing A Fair Individualized Polysocial Risk Score (iPsRS) for Identifying Increased Social Risk of Hospitalizations in Patients with Type 2 Diabetes (T2D)

Yu Huang, Jingchuan Guo, William T Donahoo, Zhengkang Fan, Ying Lu, Wei-Han Chen, Huilin Tang, Lori Bilello, Elizabeth A Shenkman, Jiang Bian

专题命中程序分析与验证：repository(abstract)；分类 cs.LG

1. 程序分析与验证 189 篇

Exploring the Feasibility of End-to-End Large Language Model as a Compiler

TypePilot: Leveraging the Scala Type System for Secure LLM-generated Code

ACT: Automatically Generating Compiler Backends from Tensor Accelerator ISA Descriptions

We've Got You Covered: Type-Guided Repair of Incomplete Input Generators

ATLANTIS: AI-driven Threat Localization, Analysis, and Triage Intelligence System

Static Analysis as a Feedback Loop: Enhancing LLM-Generated Code Beyond Correctness

Improving compiler support for SIMD offload using Arm Streaming SVE

TPDE: A Fast Adaptable Compiler Back-End Framework

eqsat: An Equality Saturation Dialect for Non-destructive Rewriting

AssertionForge: Enhancing Formal Verification Assertion Generation with Structured Representation of Specifications and RTL

Optimizing FDTD Solvers for Electromagnetics: A Compiler-Guided Approach with High-Level Tensor Abstractions

A Multi-level Compiler Backend for Accelerated Micro-kernels Targeting RISC-V ISA Extensions

Towards Semantics Lifting for Scientific Computing: A Case Study on FFT

AssetHarvester: A Static Analysis Tool for Detecting Secret-Asset Pairs in Software Artifacts

An Optimizing Just-In-Time Compiler for Rotor

FVEval: Understanding Language Model Capabilities in Formal Verification of Digital Hardware

Codellm-Devkit: A Framework for Contextualizing Code LLMs with Program Analysis Insights

Magika: AI-Powered Content-Type Detection

To Type or Not to Type? A Systematic Comparison of the Software Quality of JavaScript and TypeScript Applications on GitHub

TIGER: A Generating-Then-Ranking Framework for Practical Python Type Inference

Isolating Compiler Bugs by Generating Effective Witness Programs with Large Language Models

Enhancing Formal Theorem Proving: A Comprehensive Dataset for Training AI Models on Coq Code

oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation

LLM4VV: Developing LLM-Driven Testsuite for Compiler Validation

PyTy: Repairing Static Type Errors in Python

Petit programming language and compiler

CompCodeVet: A Compiler-guided Validation and Enhancement Approach for Code Dataset

Graph IRs for Impure Higher-Order Languages (Technical Report)

Sound Atomicity Inference for Data-Centric Synchronization

Developing A Fair Individualized Polysocial Risk Score (iPsRS) for Identifying Increased Social Risk of Hospitalizations in Patients with Type 2 Diabetes (T2D)