9 papers
SysLLMatic: Large Language Models are Software System Optimizers
Huiyun Peng, Arjun Gupte, Ryan Hasler +7
Automatic software system optimization can improve software speed, reduce operating costs, and save energy. Traditional approaches to optimization rely on manual tuning and compile…
Beyond Local Code Optimization: Multi-Agent Reasoning for Software System Optimization
Huiyun Peng, Parth Vinod Patil, Antonio Zhong Qiu +2
Large language models and AI agents have recently shown promise in automating software performance optimization, but existing approaches predominantly rely on local, syntax-driven…
AgentHub: A Registry for Discoverable, Verifiable, and Reproducible AI Agents
Erik Pautsch, Tanmay Singla, Parv Kumar +6
LLM-based agents are rapidly proliferating, yet the infrastructure for discovering, evaluating, and governing them remains fragmented compared to mature ecosystems like software pa…
How Do Agents Perform Code Optimization? An Empirical Study
Huiyun Peng, Antonio Zhong, Ricardo Andrés Calvo Méndez +2
Performance optimization is a critical yet challenging aspect of software development, often requiring a deep understanding of system behavior, algorithmic tradeoffs, and careful c…
A Guide to Stakeholder Analysis for Cybersecurity Researchers
James C Davis, Sophie Chen, Huiyun Peng +2
Stakeholder-based ethics analysis is now a formal requirement for submissions to top cybersecurity research venues. This requirement reflects a growing consensus that cybersecurity…
Recommending Pre-Trained Models for IoT Devices
Parth V. Patil, Wenxin Jiang, Huiyun Peng +7
The availability of pre-trained models (PTMs) has enabled faster deployment of machine learning across applications by reducing the need for extensive training. Techniques like qua…