T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks
Paper • 2609.11042 • Published • 53
T1
CC BY 4.0 RL checkpoints for T1; base-model and third-party terms still apply.
-
-
TberiusJunyao/T1-122B-A10B
Image-Text-to-Text • 125B • Updated • 41 • 4 -
TberiusJunyao/T1-Terminal-Bench-2.1-Trajectories
Viewer • Updated • 178 • 127 -
TberiusJunyao/T1-Long-Horizon-Terminal-Bench-Trajectories
Viewer • Updated • 92 • 76 -
TberiusJunyao/T1-Terminal-Bench-Hard-Trajectories
Viewer • Updated • 100 • 106