May 4, 2026 · cs.DCJ/K move · Enter open · S save
Arup Kumar Sarker, Mills Staylor, Aymen Alsaadi, Gregor von Laszewski+2
Department of Computer Science, Biocomplexity Institute and Initiative University of Virginia Charlottesville, VA, USA · Department of Computer Science, Rutgers University New Brunswick, NJ, USA · Biocomplexity Institute and Initiative University of Virginia Charlottesville, VA, USA · Department of Computer Science Rutgers University Princeton Plasma Physics Laboratory Princeton, NJ, USA
Agentic workflows in large language model systems integrate retrieval, reasoning, and memory, but existing frameworks suffer from scalability and reproducibility limitations due to fragmented data orchestration, serialization overhead, and non-deterministic execution. Although these frameworks increase flexibility, they don't have a formal execution model that adheres to the principles of high-performance computing. We introduce AAFLOW, a unified distributed runtime that creates communication-efficient execution plans by modeling agentic workflows as an operator abstraction. Using Apache Arrow and Cylon, AAFLOW creates a zero-copy data plane that allows direct interoperability between preprocessing, embedding, and vector retrieval without the need for serialization overhead. To lower coordination costs, it uses resource-deterministic scheduling and asynchronous batching. While retaining comparable LLM generation throughput, experimental results demonstrate up to 4.64 times pipeline speedup and 2.8 times gains in embedding and upsert phases. Rather than LLM inference acceleration, these advantages result from enhanced data flow, batching, and communication efficiency.