7 papers
Persistent Cross-Attempt State Optimization for Repository-Level Code Generation
Ruwei Pan, Jiangshuai Wang, Qisheng Zhang +6
Large language models (LLMs) have achieved substantial progress in repository-level code generation. However, solving the same repository-level task often requires multiple attempt…
Toward Executable Repository-Level Code Generation via Environment Alignment
Ruwei Pan, Junlei Shen, Linhao Wu +5
Large language models (LLMs) have achieved strong performance on code generation, but existing methods still struggle with repository-level code generation under executable validat…
Toward Functional and Non-Functional Evaluation of Application-Level Code Generation
Ruwei Pan, Yakun Zhang, Qingyuan Liang +4
Large language models (LLMs) have achieved strong performance on code generation. However, most prior evaluations focus on snippet-level outputs, such as function generation or rep…
AgentDroid: A Multi-Agent Framework for Detecting Fraudulent Android Applications
Ruwei Pan, Hongyu Zhang, Zhonghao Jiang +1
With the increasing prevalence of fraudulent Android applications such as fake and malicious applications, it is crucial to detect them with high accuracy and adaptability. We pres…
AdaCoder: An Adaptive Planning and Multi-Agent Framework for Function-Level Code Generation
Yueheng Zhu, Chao Liu, Xuan He +4
Recently, researchers have proposed many multi-agent frameworks for function-level code generation, which aim to improve software development productivity by automatically generati…
MoT: Modularization-of-Thought Prompting for Effective Code Generation
Ruwei Pan, Hongyu Zhang
Large Language Models are transforming software development by automatically generating code. Current prompting techniques such as Chain-of-Thought (CoT) suggest tasks step by step…