RadixArk DaisyRose-27B Explained: How Pure RL (No SFT) Doubled Terminal-Bench 4.1 Agent Scores
Inside the open-weight model post-trained purely through reinforcement learning on long-horizon agent tasks.
RadixArk DaisyRose-27B Explained: How Pure RL (No SFT) Doubled Terminal-Bench 4.1 Agent Scores