EPM-RL

EPM-RL is a reinforcement-learning framework from McMaster University that distills costly multi-agent LLM reasoning into a small, efficient on-premise model for product mapping, enabling accurate antibiotic discovery after exploring 46 billion compo

Two-hop subgraph: this entity, every entity it directly relates to, and every entity those neighbors relate to. Drag a node, scroll to zoom, click to inspect — or click any neighbor and re-center the atlas there.