3 papers
cs.AI2026
Configuring RAG Systems: What Breaks, Where Originates, and How to Fix
Liangyu Chen, Youpeng Ma, Yulong Ye +2
Retrieval-Augmented Generation (RAG) has emerged as a dominant paradigm for improving Large Language Model (LLM) by intertwining it with other components, such as a vector/graph da…
cs.LG2026
LLMSYS-HPOBench: Hyperparameter Optimization Benchmark Suite for Real-World LLM Systems
Siyu Wu, Yulong Ye, Zezhen Xiang +3
Large Language Model (LLM) systems have been the frontier of AI in many application domains, leading to new challenges and opportunities for hyperparameter optimization (HPO) for t…
cs.SE2025
Dually Hierarchical Drift Adaptation for Online Configuration Performance Learning
Zezhen Xiang, Jingzhi Gong, Tao Chen
Modern configurable software systems need to learn models that correlate configuration and performance. However, when the system operates in dynamic environments, the workload vari…