Art of Cyber AI — Research FeedResearch releases on reinforcement learning, LLM post-training, agent evaluation, and efficient inference.https://artofcyberai.com/2026-08-24T12:00:00-07:00Vikram Kharvihttps://artofcyberai.com/Post-training Is a Stackhttps://trainrl.com/post-training-stack2026-08-13T12:00:00-07:002026-08-24T12:00:00-07:00The full map of supervised tuning, synthetic data, preferences, reinforcement learning, safety, agent trajectories, distillation, and continual improvement.