Code Generation
Code generation research focuses on using large language models (LLMs) to automatically produce functional and secure code from natural language descriptions or other inputs. Current efforts concentrate on improving the accuracy and efficiency of code generation, including developing novel training objectives like horizon-length prediction and employing techniques such as multi-agent frameworks, Monte Carlo Tree Search, and prompt engineering to guide LLMs towards better solutions. This field is significant because it promises to dramatically increase developer productivity and accelerate software development, while also raising important questions about code security and reliability that require further investigation.
Papers
A Comprehensive Study of the Capabilities of Large Language Models for Vulnerability Detection
Benjamin Steenhoek, Md Mahbubur Rahman, Monoshi Kumar Roy, Mirza Sanjida Alam, Earl T. Barr, Wei Le
Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback
Zhangqian Bi, Yao Wan, Zheng Wang, Hongyu Zhang, Batu Guan, Fangxin Lu, Zili Zhang, Yulei Sui, Hai Jin, Xuanhua Shi
Bugs in Large Language Models Generated Code: An Empirical Study
Florian Tambon, Arghavan Moradi Dakhel, Amin Nikanjam, Foutse Khomh, Michel C. Desmarais, Giuliano Antoniol
DevBench: A Comprehensive Benchmark for Software Development
Bowen Li, Wenhan Wu, Ziwei Tang, Lin Shi, John Yang, Jinyang Li, Shunyu Yao, Chen Qian, Binyuan Hui, Qicheng Zhang, Zhiyin Yu, He Du, Ping Yang, Dahua Lin, Chao Peng, Kai Chen
Software Vulnerability and Functionality Assessment using LLMs
Rasmus Ingemann Tuffveson Jensen, Vali Tawosi, Salwa Alamir
AutoDev: Automated AI-Driven Development
Michele Tufano, Anisha Agarwal, Jinu Jang, Roshanak Zilouchian Moghaddam, Neel Sundaresan
Automatic Generation of Python Programs Using Context-Free Grammars
Kamel Yamani, Marwa Naïr, Riyadh Baghdadi
Prompt Selection and Augmentation for Few Examples Code Generation in Large Language Model and its Application in Robotics Control
On Tai Wu, Frodo Kin Sun Chan, Zunhao Zhang, Yan Nei Law, Benny Drescher, Edmond Shiao Bun Lai
InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language Models
Linyi Li, Shijie Geng, Zhenwen Li, Yibo He, Hao Yu, Ziyue Hua, Guanghan Ning, Siwei Wang, Tao Xie, Hongxia Yang
DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation
Xueqing Wu, Rui Zheng, Jingzhen Sha, Te-Lin Wu, Hanyu Zhou, Mohan Tang, Kai-Wei Chang, Nanyun Peng, Haoran Huang
CatCode: A Comprehensive Evaluation Framework for LLMs On the Mixture of Code and Text
Zhenru Lin, Yiqun Yao, Yang Yuan