Tag
A developer introduces a concept called a 'reactor' — an agent session DAG that maintains a memoized world-model using OpenProse markdown files and the openai-agents-sdk, drawing parallels to React and dataflow.
DataFlow is an open-source tool with visual, low-code pipelines to generate, clean, and prepare high-quality LLM training datasets from raw data. It includes a technical report on arXiv.
AstraFlow is a dataflow-oriented RL system that enables efficient multi-policy collaborative training and elastic scaling for agentic LLMs, achieving a 2.7x training speedup over existing systems.