5 papers
DynBranch: Speculative Subgraph Reuse for Dynamic Agentic LLM Serving
Junyi Shen, Noppanat Wadlom, Zhengyuan Su +1
Agentic LLM workflows decide their execution paths at runtime. Downstream computation may be predictable, or may have run before, yet it cannot begin until the model or the user re…
Efficient LLM Serving for Agentic Workflows: A Data Systems Perspective
Noppanat Wadlom, Junyi Shen, Yao Lu
Agentic workflows are composed of sequences of interdependent Large Language Model (LLM) calls, and they have become a dominant workload in modern AI systems. These workflows exhib…
FlowMesh: A Service Fabric for Composable LLM Workflows
Junyi Shen, Noppanat Wadlom, Lingfeng Zhou +4
AI deployment increasingly resembles a pipeline of data transformation, fine-tuning, and agent interactions rather than a monolithic LLM job; recent examples include RLHF/RLAIF tra…
Batch Query Processing and Optimization for Agentic Workflows
Junyi Shen, Noppanat Wadlom, Yao Lu
Large Language Models (LLMs) in agentic workflows combine multi-step reasoning, heterogeneous tool use, and collaboration across multiple specialized agents. Existing LLM serving e…
mCardiacDx: Radar-Driven Contactless Monitoring and Diagnosis of Arrhythmia
Arjun Kumar, Noppanat Wadlom, Jaeheon Kwak +2
Arrhythmia is a common cardiac condition that can precipitate severe complications without timely intervention. While continuous monitoring is essential for timely diagnosis, conve…