From the 1 of 7 linked papers with an AI index.
7 papers
Not as Sweet by Another Name: An Empirical Study of Format Robustness in LLM Document Workflows
Xiaoyu Zhang, Xianyun Cheng, Tianlin Li +3
The paper investigates how changing document formats (e.g., CSV vs. plain text) affects the reliability of end-to-end LLM-driven software workflows, introducing a metamorphic testi…
Rethinking Technology Stack Selection with AI Coding Proficiency
Xiaoyu Zhang, Weipeng Jiang, Shiqing Ma +5
Large language models (LLMs) are now an integral part of software development workflows and are reshaping the whole process. However, existing technology selection methods mainly f…
Weaponizing the Commons: A Taxonomy and Detection Framework of Abuse on GitHub
Yuli Cheng, Xiaoyu Zhang, Jiongchi Yu +3
GitHub plays a critical role in modern software supply chains, making its security an important research concern. Existing studies have primarily focused on CI/CD automation, colla…
Software Development Life Cycle Perspective: A Survey of Benchmarks for Code Large Language Models and Agents
Kaixin Wang, Tianlin Li, Xiaoyu Zhang +7
Code large language models (CodeLLMs) and agents are increasingly being integrated into complex software engineering tasks spanning the entire Software Development Life Cycle (SDLC…
Where Agent Frameworks Fall Short: Examining Functional Challenges and Usability Concerns
Xinxue Zhu, Jiacong Wu, Xiaoyu Zhang +6
Large language model (LLM) agents are increasingly built on agent frameworks that provide reusable abstractions for workflow orchestration, state management, tool integration, and…
BDefects4NN: A Backdoor Defect Database for Controlled Localization Studies in Neural Networks
Yisong Xiao, Aishan Liu, Xinwei Zhang +6
Pre-trained large deep learning models are now serving as the dominant component for downstream middleware users and have revolutionized the learning paradigm, replacing the tradit…