CodeV: Issue Resolving with Visual Data

1 code implementation • 23 Dec 2024 • Linhao Zhang, Daoguang Zan, Quanshun Yang, Zhirong Huang, Dong Chen, Bo Shen, Tianyu Liu, Yongshun Gong, Pengjie Huang, Xudong Lu, Guangtai Liang, Lizhen Cui, Qianxiang Wang

Large Language Models (LLMs) have advanced rapidly in recent years, with their applications in software engineering expanding to more complex repository-level tasks.

Agents in Software Engineering: Survey, Landscape, and Vision

1 code implementation • 13 Sep 2024 • Yanlin Wang, Wanjun Zhong, Yanxian Huang, Ensheng Shi, Min Yang, Jiachi Chen, Hui Li, Yuchi Ma, Qianxiang Wang, Zibin Zheng

In recent years, Large Language Models (LLMs) have achieved remarkable success and have been widely used in various downstream tasks, especially in the tasks of the software engineering (SE) field.

Survey

SWE-bench-java: A GitHub Issue Resolving Benchmark for Java

2 code implementations • 26 Aug 2024 • Daoguang Zan, Zhirong Huang, Ailun Yu, Shaoxin Lin, Yifan Shi, Wei Liu, Dong Chen, Zongshuai Qi, Hao Yu, Lei Yu, Dezhi Ran, Muhan Zeng, Bo Shen, Pan Bian, Guangtai Liang, Bei guan, Pengjie Huang, Tao Xie, Yongji Wang, Qianxiang Wang

GitHub issue resolving is a critical task in software engineering, recently gaining significant attention in both industry and academia.

CodeR: Issue Resolving with Multi-Agent and Task Graphs

1 code implementation • 3 Jun 2024 • Dong Chen, Shaoxin Lin, Muhan Zeng, Daoguang Zan, Jian-Gang Wang, Anton Cheshkov, Jun Sun, Hao Yu, Guoliang Dong, Artem Aliev, Jie Wang, Xiao Cheng, Guangtai Liang, Yuchi Ma, Pan Bian, Tao Xie, Qianxiang Wang

GitHub issue resolving recently has attracted significant attention from academia and industry.

Bug fixing

CodeS: Natural Language to Code Repository via Multi-Layer Sketch

2 code implementations • 25 Mar 2024 • Daoguang Zan, Ailun Yu, Wei Liu, Dong Chen, Bo Shen, Wei Li, Yafen Yao, Yongshun Gong, Xiaolin Chen, Bei guan, Zhiguang Yang, Yongji Wang, Qianxiang Wang, Lizhen Cui

For feedback-based evaluation, we develop a VSCode plugin for CodeS and engage 30 participants in conducting empirical studies.

Benchmarking

Can Programming Languages Boost Each Other via Instruction Tuning?

no code implementations • 31 Aug 2023 • Daoguang Zan, Ailun Yu, Bo Shen, Jiaxin Zhang, Taihong Chen, Bing Geng, Bei Chen, Jichuan Ji, Yafen Yao, Yongji Wang, Qianxiang Wang

Results demonstrate that programming languages can significantly improve each other.

HumanEval

PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback

no code implementations • 27 Jul 2023 • Bo Shen, Jiaxin Zhang, Taihong Chen, Daoguang Zan, Bing Geng, An Fu, Muhan Zeng, Ailun Yu, Jichuan Ji, Jingyang Zhao, Yuenan Guo, Qianxiang Wang

In this paper, we propose a novel RRTF (Rank Responses to align Test&Teacher Feedback) framework, which can effectively and efficiently boost pre-trained large language models for code generation.

Code Generation HumanEval

PanGu-Coder: Program Synthesis with Function-Level Language Modeling

1 code implementation • 22 Jul 2022 • Fenia Christopoulou, Gerasimos Lampouras, Milan Gritta, Guchun Zhang, Yinpeng Guo, Zhongqi Li, Qi Zhang, Meng Xiao, Bo Shen, Lin Li, Hao Yu, Li Yan, Pingyi Zhou, Xin Wang, Yuchi Ma, Ignacio Iacobacci, Yasheng Wang, Guangtai Liang, Jiansheng Wei, Xin Jiang, Qianxiang Wang, Qun Liu

We present PanGu-Coder, a pretrained decoder-only language model adopting the PanGu-Alpha architecture for text-to-code generation, i. e. the synthesis of programming language solutions given a natural language problem description.

Code Generation Decoder +4