Ying Wen — BlogThoughts on agentic RL, multi-agent systems, and AI research.https://yingwen.io/enWhen Agents Learn from the World, Not from Ushttps://yingwen.io/en/blog/when-agents-learn-from-world/https://yingwen.io/en/blog/when-agents-learn-from-world/The pretraining paradigm scaled data. The agent paradigm scales environments. Three observations on environment scaling, continuous evolution, and multi-agent collaboration.Sun, 15 Mar 2026 00:00:00 GMT