This paper introduces a foundational step-level routing paradigm that treats multi-model coordination within agent execution harnesses as a dynamic, state-conditioned systems problem. It establishes a harness-native data flywheel where execution traces and environmental feedback automatically train better routers and specialized models, offering a self-improving data engine for scaling agent infrastructure.
Short on time? Watch the video overview of this paper.
Listen on: Spotify · Apple Podcasts · Amazon Music · YouTube
Follow the show: YouTube · Medium · X · LinkedIn · Bluesky · Threads · Instagram · TikTok · Facebook · Telegram