view article Article Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps +1 iamleonie, burtenshaw, sergiopaniego • 27 days ago • 139
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments Paper • 2609.04148 • Published 27 days ago • 248
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses Paper • 2609.24972 • Published 9 days ago • 217