The models and techniques required to build fully autonomous coding agents - not just coding copilots - are already emerging. In this talk, Aakanksha Chowdhery, former lead researcher on Gemini and now Research Lead at Reflection, will present the latest research trends on enabling post-training advancements in open-weight LLMs for autonomous SWE tasks. She'll focus on how scaling LLMs with Reinforcement Learning improves the autonomous coding capabilities of LLMs, and provide insight on the technical challenges required to train such systems at scale.