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
Towards LLM-based optimization compilers. Can LLMs learn how to apply a single peephole optimization? Reasoning is all LLMs need!
Xiangxin Fang, Lev Mukhanov
Unseen Horizons: Unveiling the Real Capability of LLM Code Generation Beyond the Familiar
Yuanliang Zhang, Yifan Xie, Shanshan Li, Ke Liu, Chong Wang, Zhouyang Jia, Xiangbing Huang, Jie Song, Chaopeng Luo, Zhizheng Zheng, Rulin Xu, Yitong Liu, Si Zheng, Xiangke Liao
What You See Is Not Always What You Get: An Empirical Study of Code Comprehension by Large Language Models
Bangshuo Zhu, Jiawen Wen, Huaming Chen
DialogAgent: An Auto-engagement Agent for Code Question Answering Data Production
Xiaoyun Liang, Jingyi Ren, Jiayi Qi, Chao Peng, Bo Jiang
A Comparative Study on Code Generation with Transformers
Namrata Das, Rakshya Panta, Neelam Karki, Ruchi Manandhar, Dinesh Baniya Kshatri
Can Large Language Models Help Developers with Robotic Finite State Machine Modification?
Xiangyu Robin Gan, Yuxin Ray Song, Nick Walker, Maya Cakmak
GEE-OPs: An Operator Knowledge Base for Geospatial Code Generation on the Google Earth Engine Platform Powered by Large Language Models
Shuyang Hou, Jianyuan Liang, Anqi Zhao, Huayi Wu
HiVeGen -- Hierarchical LLM-based Verilog Generation for Scalable Chip Design
Jinwei Tang, Jiayin Qin, Kiran Thorat, Chen Zhu-Tian, Yu Cao, Yang (Katie) Zhao, Caiwen Ding
Enhancing Cross-Language Code Translation via Task-Specific Embedding Alignment in Retrieval-Augmented Generation
Manish Bhattarai, Minh Vu, Javier E. Santos, Ismael Boureima, Daniel O' Malley
Code generation and runtime techniques for enabling data-efficient deep learning training on GPUs
Kun Wu
Does Few-Shot Learning Help LLM Performance in Code Synthesis?
Derek Xu, Tong Xie, Botao Xia, Haoyu Li, Yunsheng Bai, Yizhou Sun, Wei Wang
A Multi-Agent Framework for Extensible Structured Text Generation in PLCs
Donghao Yang, Aolang Wu, Tianyi Zhang, Li Zhang, Fang Liu, Xiaoli Lian, Yuming Ren, Jiaji Tian
Instruct or Interact? Exploring and Eliciting LLMs' Capability in Code Snippet Adaptation Through Prompt Engineering
Tanghaoran Zhang, Yue Yu, Xinjun Mao, Shangwen Wang, Kang Yang, Yao Lu, Zhang Zhang, Yuxin Zhao
A Preliminary Study of Multilingual Code Language Models for Code Generation Task Using Translated Benchmarks
Rohit Dandamudi, Gema Rodríguez-Pérez