Jinyun Yang

SAGE: A Dataflow-Native Framework for Modular, Controllable, and Transparent LLM-Augmented Reasoning

LLM applications increasingly execute as end-to-end inference pipelines that couple generation with retrieval, stateful memory, context refinement, and tool use under strict tail-latency and SLO constraints. Today, these stages are often stitched together as RPC-connected services, obscuring cross-s…